@prismer/runtime 2.2.55 → 2.2.63

package/built-in-skills/skill-creator/eval-viewer/viewer.html

@@ -652,19 +652,27 @@
     let feedbackMap = {};  // run_id -> feedback text
     let currentIndex = 0;
     let visitedRuns = new Set();
+    let reviewComplete = false;
+    let saveQueue = Promise.resolve();
+    function postFeedback(payload) {
+      saveQueue = saveQueue.catch(() => {}).then(async () => {
+        const response = await fetch('/api/feedback', {
+          method: 'POST', headers: { 'Content-Type': 'application/json' },
+          body: JSON.stringify(payload),
+        });
+        if (!response.ok) throw new Error('Feedback save failed');
+      });
+      return saveQueue;
+    }
 
     // ---- Init ----
     async function init() {
-      // Load saved feedback from server — but only if this isn't a fresh
-      // iteration (indicated by previous_feedback being present). When
-      // previous feedback exists, the feedback.json on disk is stale from
-      // the prior iteration and should not pre-fill the textareas.
-      const hasPrevious = Object.keys(EMBEDDED_DATA.previous_feedback || {}).length > 0
-        || Object.keys(EMBEDDED_DATA.previous_outputs || {}).length > 0;
-      if (!hasPrevious) {
+      // Current workspace feedback is distinct from previous-workspace context.
+      {
         try {
           const resp = await fetch("/api/feedback");
           const data = await resp.json();
+          reviewComplete = data.status === 'complete';
           if (data.reviews) {
             for (const r of data.reviews) feedbackMap[r.run_id] = r.feedback;
           }
@@ -678,6 +686,7 @@
       const textarea = document.getElementById("feedback");
       let saveTimeout = null;
       textarea.addEventListener("input", () => {
+        reviewComplete = false;
         clearTimeout(saveTimeout);
         document.getElementById("feedback-status").textContent = "";
         saveTimeout = setTimeout(() => saveCurrentFeedback(), 800);
@@ -803,6 +812,7 @@
           content.appendChild(img);
         } else if (file.type === "pdf") {
           const iframe = document.createElement("iframe");
+          iframe.setAttribute('sandbox', '');
           iframe.src = file.data_uri;
           content.appendChild(iframe);
         } else if (file.type === "xlsx") {
@@ -844,10 +854,18 @@
             container.appendChild(sheetLabel);
           }
 
-          const htmlStr = XLSX.utils.sheet_to_html(ws, { editable: false });
-          const wrapper = document.createElement("div");
-          wrapper.innerHTML = htmlStr;
-          container.appendChild(wrapper);
+          const table = document.createElement('table');
+          // Cell values and hyperlinks are untrusted; never insert workbook HTML.
+          for (const row of XLSX.utils.sheet_to_json(ws, { header: 1, defval: '' })) {
+            const tr = document.createElement('tr');
+            for (const value of row) {
+              const td = document.createElement('td');
+              td.textContent = String(value);
+              tr.appendChild(td);
+            }
+            table.appendChild(tr);
+          }
+          container.appendChild(table);
         }
       } catch (err) {
         container.textContent = "Error rendering spreadsheet: " + err.message;
@@ -963,6 +981,7 @@
           fc.appendChild(img);
         } else if (file.type === "pdf") {
           const iframe = document.createElement("iframe");
+          iframe.setAttribute('sandbox', '');
           iframe.src = file.data_uri;
           fc.appendChild(iframe);
         } else if (file.type === "xlsx") {
@@ -992,6 +1011,7 @@
 
     // ---- Feedback (saved to server -> feedback.json) ----
     function saveCurrentFeedback() {
+      if (reviewComplete) return;
       const run = EMBEDDED_DATA.runs[currentIndex];
       const text = document.getElementById("feedback").value;
 
@@ -1009,11 +1029,7 @@
         }
       }
 
-      fetch("/api/feedback", {
-        method: "POST",
-        headers: { "Content-Type": "application/json" },
-        body: JSON.stringify({ reviews, status: "in_progress" }),
-      }).then(() => {
+      postFeedback({ reviews, status: 'in_progress' }).then(() => {
         document.getElementById("feedback-status").textContent = "Saved";
       }).catch(() => {
         // Static mode or server unavailable — no-op on auto-save,
@@ -1041,11 +1057,8 @@
         reviews.push({ run_id: r.id, feedback: feedbackMap[r.id] || "", timestamp: ts });
       }
       const payload = JSON.stringify({ reviews, status: "complete" }, null, 2);
-      fetch("/api/feedback", {
-        method: "POST",
-        headers: { "Content-Type": "application/json" },
-        body: payload,
-      }).then(() => {
+      reviewComplete = true;
+      postFeedback({ reviews, status: 'complete' }).then(() => {
         document.getElementById("done-overlay").classList.add("visible");
       }).catch(() => {
         // Server not available (static mode) — download as file
@@ -1061,8 +1074,7 @@
     }
 
     function closeDoneDialog() {
-      // Reset status back to in_progress
-      saveCurrentFeedback();
+      // Closing the acknowledgement does not reopen a completed review.
       document.getElementById("done-overlay").classList.remove("visible");
     }
 

package/built-in-skills/skill-creator/references/hermes-agent-skill-authoring/GUIDE.md

@@ -0,0 +1,220 @@
+---
+name: hermes-agent-skill-authoring
+description: "Author in-repo SKILL.md files: frontmatter and structure."
+version: 2.0.0
+author: Hermes Agent
+license: MIT
+platforms: [linux, macos, windows]
+metadata:
+  hermes:
+    tags: [skills, authoring, hermes-agent, conventions, skill-md]
+    related_skills: [requesting-code-review]
+---
+
+# Authoring Hermes-Agent Skills (in-repo)
+
+> Prismer adaptation: this reference describes Hermes-specific standards, not
+> the Prismer catalog schema. Resolve the actual repository root before using
+> any relative path. Hermes tools and directories apply only inside a verified
+> Hermes checkout. Never stage, commit, publish, or restore files automatically.
+> Preserve every pre-existing change. Usage-frequency thresholds below are
+> upstream guidance, not evidence for deleting existing Prismer skills.
+
+## Overview
+
+There are two places a SKILL.md can live:
+
+1. **User-local:** `~/.hermes/skills/<maybe-category>/<name>/SKILL.md` — personal, not shared. Created via `skill_manage(action='create')`.
+2. **In-repo (this skill is about this case):** `skills/<category>/<name>/SKILL.md` or `optional-skills/<category>/<name>/SKILL.md` inside the hermes-agent repo — committed, shipped with the package. Use the available file-editing tool; stage only on explicit user request. `skill_manage(action='create')` does NOT target this tree.
+
+In-repo skills must meet the repo's **hardline authoring standards** (see AGENTS.md, "Skill authoring standards (HARDLINE)" — that section is the source of truth; this skill is the operational walkthrough). Reviewers reject PRs that violate them, so meeting them up front is cheaper than a salvage pass later.
+
+## When to Use
+
+- User asks you to add a skill "in this branch / repo / commit"
+- You're committing a reusable workflow that should ship with hermes-agent
+- You're editing an existing skill under `skills/` or `optional-skills/` (use `patch` for small edits, `write_file` for rewrites; `skill_manage` still works for patch on in-repo skills, but not for `create`)
+- Don't use for: personal skills in `~/.hermes/skills/` (just use `skill_manage`)
+
+## Decide the Tier First: Bundled vs Optional
+
+- **Bundled (`skills/<category>/`)** — daily-driver behavior, broadly useful across many user types, low footprint. Hard bar: you can say "a user will load this in 5+ sessions per month" with a straight face.
+- **Optional (`optional-skills/<category>/`)** — niche, vertical-specific (blockchain, gaming, finance, one app), recurring-job/task skills, or anything heavy. Installed via `hermes skills install official/<category>/<skill>`.
+
+**When in doubt, optional.** Promoting later is easy; demoting is churn. "Would be useful to anyone who ever needs this" is an optional-tier argument, not a bundled one.
+
+Pick the category by what the tool IS, not what it feels like (an AI-agent CLI goes in `autonomous-ai-agents/` even if it "feels productivity"). Confirm existing categories with `search_files(pattern='*', target='files', path='skills')` and don't invent new top-level categories casually.
+
+**No router / index / hub skills.** A skill whose core content is a routing table pointing at sibling skills adds an indirection hop and duplicates the siblings' own `When to Use` triggers. If the skill would be empty without "load skill X instead" pointers, don't write it — the catalog and each sibling's triggers already do that job.
+
+## Required Frontmatter
+
+Validator source of truth: `tools/skill_manager_tool.py::_validate_frontmatter`. Validator hard requirements:
+
+- Starts with `---` as the first bytes (no leading blank line).
+- Closes with `\n---\n` before the body.
+- Parses as a YAML mapping.
+- `name` field present.
+- `description` field present (validator ceiling 1024 chars — but see the repo hardline below, which is much stricter).
+- Non-empty body after the closing `---`.
+
+Repo-standard shape (all fields expected, even where the validator doesn't enforce them):
+
+```yaml
+---
+name: my-skill-name               # lowercase, hyphens, ≤64 chars (MAX_NAME_LENGTH)
+description: Concise capability statement, under sixty chars.
+version: 0.1.0                    # semver; new skills start at 0.1.0
+author: Real Name (github-handle), Hermes Agent
+license: MIT
+platforms: [linux, macos, windows]   # audit, don't guess — see Platform Gating
+metadata:
+  hermes:
+    tags: [Short, Descriptive, Tags]
+    related_skills: [other-in-repo-skill]
+---
+```
+
+### `description` rules (HARDLINE — the validator's 1024 is NOT the standard)
+
+- **≤ 60 characters.** One sentence. Ends with a period.
+- State the capability, not the implementation, and don't repeat the skill name.
+- No marketing words ("powerful", "comprehensive", "seamless", "advanced").
+- The system prompt skill index truncates at 57 chars + "..." — the trigger/capability must be self-contained in that window.
+- If the description contains a `:`, wrap it in double quotes or YAML parses it as a mapping and the docs generator crashes. Quotes don't count toward the 60.
+
+Good: `Track named companies for material news with cited digests.`
+Bad: `Use when a user asks to monitor named competitors or companies for product launches, pricing changes, funding, ...` (240 chars — rejected in review)
+
+### `author` rules
+
+- Credit the **human first**, then "Hermes Agent" as secondary collaborator: `Ben Barclay (benbarclay), Hermes Agent`.
+- Never `author: Hermes Agent` alone for contributed skills — credit the human, not the tool, even (especially) when an agent drafted the text.
+- Maintainer-authored skills: `Teknium (teknium1), Hermes Agent`.
+
+### `related_skills` rules
+
+- Every entry must resolve to an existing **in-repo** skill in the same tree state as your PR. Do not reference skills that were only planned, live in another PR, or exist only in `~/.hermes/skills/`.
+- Verify each entry: `search_files(pattern='<name>', target='files', path='skills')` (and `optional-skills/`).
+
+## Platform Gating: audit, don't trust
+
+`platforms:` gates loading by host OS. Set it from what the skill's prose and scripts actually invoke:
+
+| Skill uses only… | `platforms:` |
+|---|---|
+| Hermes tools + stdlib Python + cross-platform CLIs | `[linux, macos, windows]` |
+| bash pipelines, `grep`/`awk`/`sed` chains, heredocs | `[linux, macos]` |
+| `osascript`, `defaults`, `pmset` | `[macos]` |
+| `apt`/`systemctl`/`/proc` | `[linux]` |
+
+<!-- no-tmp: ok — names the anti-pattern skill authors must avoid -->
+POSIX-only signals to search for in `scripts/`: `fcntl`, `termios`, `pty`, `os.fork`, `os.killpg`, `signal.SIGKILL`, `os.kill(pid, 0)` liveness checks, hardcoded `/tmp` `/proc` `/etc`. Default posture: fix cross-platform first (`tempfile.gettempdir()`, `pathlib.Path`, `psutil.pid_exists`); gate narrower only when the dependency is genuinely platform-bound, and say why in `## Pitfalls`.
+
+## Size Limits
+
+- Full SKILL.md: ≤ 100,000 chars enforced (`MAX_SKILL_CONTENT_CHARS`), but target **~100 lines for a simple skill, ~200 for a complex one**. Peer skills sit at 8-14k chars.
+- Bulky or branch-specific material goes in `references/*.md`, `templates/`, or `scripts/` — pointed to from SKILL.md, not inlined.
+- Don't expect the model to inline-write parsers or non-trivial logic every call — ship a helper script in `scripts/` and reference it by path.
+
+## Body Structure (modern section order)
+
+```
+# <Skill> Skill
+2-3 sentence intro: what it does, what it doesn't do, dependency stance.
+
+## When to Use          — bulleted triggers (+ "Don't use for:" counter-triggers)
+## Prerequisites        — exact env vars, installs, API key sourcing
+## How to Run           — canonical invocation through the `terminal` tool
+## Quick Reference      — flat command list, no narration
+## Procedure            — numbered steps, each with a checkable completion criterion
+## Pitfalls             — known limits, things that look broken but aren't
+## Verification         — how to prove the skill worked
+```
+
+Not every section applies to every skill (a pure-procedure task skill may have no Quick Reference), but When to Use + actionable body + Pitfalls + Verification are the minimum. Cut marketing intros, "Setup Check" no-ops, and re-explanations of env vars already in Prerequisites.
+
+### Reference Hermes tools, not raw shell
+
+When the skill needs a capability, name the proper Hermes tool in backticks: `terminal`, `read_file`, `write_file`, `patch`, `search_files`, `web_search`, `web_extract`, `browser_navigate`, `vision_analyze`, `delegate_task`, `cronjob`. Do NOT name shell utilities the agent already has wrapped (`grep` → `search_files`, `cat` → `read_file`, `sed`/`awk` → `patch`, `find`/`ls` → `search_files target='files'`). A CLI-wrapper skill should frame invocations as `terminal(command="<tool> ...", timeout=...)` — bare shell prose ("run `foo --version`") is a review-blocking non-conformance. If the skill depends on an MCP server, name it and document setup in Prerequisites.
+
+### Never use machine-local paths
+
+Write repo-relative paths (`skills/...`, `tools/skill_manager_tool.py`). A `/home/<you>/...` path baked into a committed skill breaks for every other user and is an instant review flag.
+
+## Writing Quality Principles
+
+A skill exists to make the agent's process more predictable — the agent reliably follows the same useful discipline.
+
+1. **Optimize for process predictability.** If a line does not change behavior, cut it.
+2. **Choose the right context load.** The description is paid for every turn; details go in the body or linked references.
+3. **End steps with completion criteria.** Checkable and, when it matters, exhaustive: "every modified file accounted for" beats "summarize changes."
+4. **Co-locate rules with the concept they govern.**
+5. **Use strong leading words** ("tight loop," "root cause," "regression test") over long repeated explanations.
+6. **Prune duplication and no-ops.** "Be careful" and "use best practices" don't change model behavior — replace with a checkable criterion or delete.
+
+## Tests and Docs (required for repo skills)
+
+1. **Tests** live at `tests/skills/test_<skill>_skill.py` — stdlib + pytest + `unittest.mock` only, no live network. Run via `scripts/run_tests.sh tests/skills/test_<skill>_skill.py -q`. (The generic `tests/tools/test_skill_manager_tool.py` passing proves nothing about YOUR skill.)
+2. **Docs regen:** run `python website/scripts/generate-skill-docs.py`, then apply scope discipline — the generator rewrites EVERY auto-gen page. run the generator in an isolated temporary checkout and copy only the intended generated files back after comparing with the current worktree; never restore unrelated changes; the final diff must show only your SKILL.md, your one per-skill docs page, a one-line catalog row, and a one-line `website/sidebars.ts` insertion (verify with `search_files(pattern='<your-slug>', path='website/sidebars.ts')` — exactly one hit, or the page is an orphan).
+3. **`.env.example`** (only if the skill needs new env vars): one clearly delimited commented block; touch nothing else in the file.
+
+## Workflow
+
+1. **Survey peers** in the target category with `search_files(target='files')` and read 2-3 peer SKILL.md files to match tone and structure. Prefer extending an existing skill over creating a narrow sibling.
+2. **Decide tier and category** (see above). When in doubt, optional — and ask before pushing rather than defaulting.
+3. **Draft** with `write_file` to `skills/<category>/<name>/SKILL.md` (or `optional-skills/...`).
+4. **Validate locally**:
+   ```python
+   import yaml, re, pathlib
+   content = pathlib.Path("skills/<category>/<name>/SKILL.md").read_text()
+   assert content.startswith("---")
+   m = re.search(r'\n---\s*\n', content[3:])
+   fm = yaml.safe_load(content[3:m.start()+3])
+   assert "name" in fm and "description" in fm
+   assert len(fm["description"]) <= 60, f"description {len(fm['description'])} chars — hardline is 60"
+   assert fm["description"].endswith(".")
+   assert "platforms" in fm
+   assert len(content) <= 100_000
+   ```
+   Also verify every `related_skills` entry exists in-repo.
+5. **Add tests + regen docs** (previous section).
+6. **Review the scoped diff** on the active branch. Stage, commit, or open a PR only when the user explicitly requests that operation.
+7. **Note:** the CURRENT session's skill loader is cached — `skill_view` / `skills_list` will not see the new skill until a new session. This is expected, not a bug.
+
+## Editing Existing In-Repo Skills
+
+- **Small fix:** `skill_manage(action='patch', ...)` works on in-repo skills, as does `patch`.
+- **Major rewrite:** `write_file` the whole SKILL.md.
+- **Supporting files:** `write_file` to `references/`, `templates/`, or `scripts/` under the skill dir.
+- **Review before commit** — in-repo skills are source, not runtime state. Never commit automatically. Regenerate docs in an isolated checkout when frontmatter changes.
+
+## Common Pitfalls
+
+1. **Using `skill_manage(action='create')` for an in-repo skill.** It writes to `~/.hermes/skills/`, not the repo tree. Use `write_file`.
+2. **Trusting the validator's limits as the standard.** The validator allows 1024-char descriptions; review rejects anything over 60. The validator doesn't check `platforms:`, author format, tests, or docs — review does.
+3. **`author: Hermes Agent` on a contributed skill.** Credit the human first.
+4. **Leading whitespace before `---`.** Validation fails on any leading blank line or BOM.
+5. **Description too generic or trigger buried past char 57.**
+6. **`related_skills` pointing at skills that don't exist in-repo** (user-local, planned, or in a sibling PR).
+7. **Duplicating a peer.** Survey the category first; extend rather than sibling.
+8. **Skipping the docs generator or pushing its unrelated drift.** Both directions are wrong: no regen = orphan skill with no docs page; blind regen = a ballooned diff full of other skills' drift.
+9. **Expecting the current session to see the new skill.** The loader is initialized at session start.
+10. **Letting skills accumulate sediment.** When adding a rule, remove the old wording it replaces.
+
+## Verification Checklist
+
+- [ ] Tier decided deliberately; the upstream 5+ sessions/month heuristic must not be treated as measured usage or used to delete existing skills
+- [ ] File at `skills/<category>/<name>/SKILL.md` or `optional-skills/<category>/<name>/SKILL.md`
+- [ ] Frontmatter starts at byte 0 with `---`, closes with `\n---\n`
+- [ ] `name`, `description`, `version`, `author`, `license`, `platforms`, `metadata.hermes.{tags, related_skills}` all present
+- [ ] Description ≤ 60 chars, one sentence, ends with a period, no marketing words
+- [ ] `author` credits the human contributor first
+- [ ] `platforms:` audited against actual prose/scripts, not copied from a sibling
+- [ ] Every `related_skills` entry resolves in-repo
+- [ ] Body follows the modern section order; commands framed through Hermes tools
+- [ ] No machine-local paths anywhere in the file
+- [ ] Each ordered step has a checkable completion criterion
+- [ ] Tests at `tests/skills/test_<skill>_skill.py` pass under `scripts/run_tests.sh`
+- [ ] Docs regenerated with scope discipline; sidebar has exactly one entry for the slug
+- [ ] Scoped diff verified; any staging, commit, or PR explicitly authorized by the user

package/built-in-skills/skill-creator/references/hermes-agent-skill-authoring/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Nous Research
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/built-in-skills/{skill-authoring/SKILL.md → skill-creator/references/skill-authoring/GUIDE.md}

@@ -130,5 +130,5 @@ blocking failure. Run the same checks locally first (or just `cloud skill valida
 ## Reference
 
 - The skill author (use this): `built-in-skills/skill-creator/SKILL.md`
-- Direct-publish tier: `built-in-skills/skill-builder/SKILL.md`
+- Direct-publish tier: `built-in-skills/skill-creator/references/skill-builder/GUIDE.md`
 - Bundle + catalog contract: `public/docs/Standardization/01-skill-standard.md` (SS-01)

package/built-in-skills/{skill-builder/SKILL.md → skill-creator/references/skill-builder/GUIDE.md}

@@ -85,21 +85,17 @@ cloud skill create ./<slug> --install --json
 # POST /api/im/skills (+ install). Reads api key from prismer config.
 ```
 
-When the `cloud` CLI binary is not on PATH (CI / SDK-only environments), use the
-bundled zero-dependency ingest script:
+The legacy script entrypoint is retained as a Cloud CLI adapter. It requires
+`cloud` on PATH (or `PRISMER_CLOUD_BIN` pointing to the current build):
 
 ```bash
-PRISMER_API_KEY=sk-prismer-...  PRISMER_CLOUD_BASE=http://127.0.0.1:3000 \
-  node scripts/ingest.mjs ./<slug> --install
+# Credentials come from the injected environment, never literal command text.
+node references/skill-builder/scripts/ingest.mjs ./<slug> --install
 ```
 
-`scripts/ingest.mjs` parses the SKILL.md frontmatter, collects every bundle file
-into an SS-01 `contentManifest`, computes the merkle `contentManifestRevision`
-with the exact server algorithm
-(`sha256(sorted("<path>:<sha256(bytes)>").join("\n"))`), `POST`s to
-`/api/im/skills` with `Authorization: Bearer $PRISMER_API_KEY`, and on
-`--install` follows with `POST /api/im/skills/:slug/install`. Both paths only
-need an **API key** (`authMiddleware` accepts `sk-prismer-*` as a Bearer token).
+The adapter delegates frontmatter parsing, complete resource/NOTICE inclusion,
+manifest hashing and install error handling to `cloud skill create`. It does
+not perform raw HTTP fallback or implement a separate YAML parser.
 
 If `cloud` is present but `skill create` is missing, that is CLI version skew,
 not permission to bypass the lifecycle. Report `cloud --version` and use the
@@ -166,6 +162,6 @@ administrator"); an admin must reinstate it first.
 
 - The skill author (use this): `built-in-skills/skill-creator/SKILL.md`
 - Bundle + catalog contract: `public/docs/Standardization/01-skill-standard.md` (SS-01)
-- Draft-gated tier: `built-in-skills/skill-authoring/SKILL.md`
+- Draft-gated tier: `built-in-skills/skill-creator/references/skill-authoring/GUIDE.md`
 - Role side: `built-in-skills/role-builder/SKILL.md` (SS-02)
 - Post-publish endpoint contract: `docs/api/publish-lifecycle.md` (product204/21)

package/built-in-skills/skill-creator/references/skill-builder/scripts/ingest.mjs

@@ -0,0 +1,93 @@
+#!/usr/bin/env node
+// skill-builder ingest — material→bundle→live catalog, via SDK + API key.
+//
+// Zero runtime dependencies (Node ≥18 built-ins only). Reads a SS-01 skill
+// bundle directory, parses SKILL.md frontmatter, builds an SS-01 contentManifest
+// with a server-matching merkle revision, and POSTs it to the real catalog
+// endpoint authenticated with an `sk-prismer-*` API key.
+//
+// Usage:
+//   PRISMER_API_KEY=sk-prismer-... [PRISMER_CLOUD_BASE=http://127.0.0.1:3000] \
+//     node scripts/ingest.mjs <bundle-dir> [--install] [--agent <imUserId>] [--json]
+//
+// Env:
+//   PRISMER_API_KEY   (required) Bearer token; admin not required for skill create.
+//   PRISMER_CLOUD_BASE (default http://127.0.0.1:3000) cloud base URL.
+
+import { spawnSync } from 'node:child_process';
+
+function die(msg, code = 1) {
+  console.error(`[skill-builder] ✗ ${msg}`);
+  process.exit(code);
+}
+
+const args = process.argv.slice(2);
+const secretOptions = new Set(['--api-key', '--token', '--jwt', '--secret', '--password']);
+let bundleDir;
+let wantInstall = false;
+let asJson = false;
+let agentId;
+for (let index = 0; index < args.length; index += 1) {
+  const arg = args[index];
+  const equalsAt = arg.indexOf('=');
+  const option = equalsAt === -1 ? arg : arg.slice(0, equalsAt);
+  if (secretOptions.has(option)) {
+    die(`${option} is forbidden; credentials must come from environment variables`, 2);
+  }
+  if (arg === '--install') {
+    wantInstall = true;
+    continue;
+  }
+  if (arg === '--json') {
+    asJson = true;
+    continue;
+  }
+  if (arg === '--agent') {
+    const value = args[index + 1];
+    if (!value || value.startsWith('--')) die('--agent requires an imUserId', 2);
+    agentId = value;
+    index += 1;
+    continue;
+  }
+  if (arg.startsWith('--')) die(`unknown argument at position ${index + 1}`, 2);
+  if (bundleDir) die('only one bundle directory may be supplied', 2);
+  bundleDir = arg;
+}
+
+const API_KEY = process.env.PRISMER_API_KEY;
+const BASE = (process.env.PRISMER_CLOUD_BASE || 'http://127.0.0.1:3000').replace(/\/$/, '');
+
+if (!bundleDir) die('usage: node ingest.mjs <bundle-dir> [--install] [--agent <imUserId>] [--json]');
+if (!API_KEY) die('PRISMER_API_KEY env is required (sk-prismer-*)');
+let target;
+try {
+  target = new URL(BASE);
+} catch {
+  die('PRISMER_CLOUD_BASE must be a valid URL', 2);
+}
+if (
+  !['http:', 'https:'].includes(target.protocol) ||
+  target.username ||
+  target.password ||
+  target.search ||
+  target.hash || target.pathname !== '/'
+) {
+  die('PRISMER_CLOUD_BASE must be a plain http(s) origin without credentials, query, or hash', 2);
+}
+const isLocalTarget = ['localhost', '127.0.0.1', '::1', 'host.docker.internal'].includes(target.hostname);
+const allowRemote = ['1', 'true', 'yes'].includes(String(process.env.PRISMER_ALLOW_REMOTE_WRITE).toLowerCase());
+if (!isLocalTarget && !allowRemote) {
+  die('remote mutation is blocked; set PRISMER_ALLOW_REMOTE_WRITE=1 after confirming the target environment', 2);
+}
+
+// Keep the legacy entrypoint, but use the canonical structured parser and CLI.
+const command = ['skill', 'create', bundleDir];
+if (wantInstall) command.push('--install');
+if (agentId) command.push('--agent', agentId);
+if (asJson) command.push('--json');
+const result = spawnSync(process.env.PRISMER_CLOUD_BIN || 'cloud', command, {
+  stdio: 'inherit', shell: false, timeout: 120_000,
+  env: { ...process.env, PRISMER_CLOUD_BASE: BASE },
+});
+if (result.error) die('Cloud CLI failed or timed out; inspect remote state before retrying', 5);
+process.exitCode = result.status ?? 5;

package/built-in-skills/skill-creator/scripts/aggregate_benchmark.py

@@ -150,7 +150,8 @@ def load_run_results(benchmark_dir: Path) -> dict:
                 metrics = grading.get("execution_metrics", {})
                 result["tool_calls"] = metrics.get("total_tool_calls", 0)
                 if not result.get("tokens"):
-                    result["tokens"] = metrics.get("output_chars", 0)
+                    result["tokens"] = metrics.get("total_tokens", 0)
+                result["output_chars"] = metrics.get("output_chars", 0)
                 result["errors"] = metrics.get("errors_encountered", 0)
 
                 # Extract expectations — viewer requires fields: text, passed, evidence
@@ -268,7 +269,7 @@ def generate_benchmark(benchmark_dir: Path, skill_name: str = "", skill_path: st
             "analyzer_model": "<model-name>",
             "timestamp": datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ"),
             "evals_run": eval_ids,
-            "runs_per_configuration": 3
+            "runs_per_configuration": {config: len(entries) for config, entries in results.items()}
         },
         "runs": runs,
         "run_summary": run_summary,

package/built-in-skills/skill-creator/scripts/import-library.mjs

@@ -1,7 +1,7 @@
 #!/usr/bin/env node
 
 import { createHash } from 'node:crypto';
-import { existsSync, mkdirSync, readFileSync, readdirSync, renameSync, statSync, writeFileSync } from 'node:fs';
+import { existsSync, mkdirSync, readFileSync, readdirSync, renameSync, statSync, writeFileSync, openSync, closeSync, unlinkSync } from 'node:fs';
 import { spawnSync } from 'node:child_process';
 import { dirname, relative, resolve, sep } from 'node:path';
 
@@ -19,7 +19,7 @@ export class LibraryImportError extends Error {
 const SECRET_OPTIONS = new Set(['--api-key', '--token', '--jwt', '--secret', '--password']);
 const BOOLEAN_OPTIONS = new Set(['--json', '--preflight-only', '--help']);
 const IGNORED_DIRECTORIES = new Set(['.git', '.prismer', 'node_modules']);
-const BUNDLE_EXCLUDED_FILES = new Set(['.DS_Store', 'Thumbs.db', 'LICENSE', 'LICENSE.txt', 'LICENSE.md']);
+const BUNDLE_EXCLUDED_FILES = new Set(['.DS_Store', 'Thumbs.db']);
 
 function optionName(arg) {
   const equalsAt = typeof arg === 'string' ? arg.indexOf('=') : -1;
@@ -96,7 +96,7 @@ export function loadLibraryImportConfig(argv, env = process.env) {
     baseUrl.username ||
     baseUrl.password ||
     baseUrl.search ||
-    baseUrl.hash
+    baseUrl.hash || baseUrl.pathname !== '/'
   ) {
     throw new LibraryImportError(
       'local_validation',
@@ -122,6 +122,7 @@ export function loadLibraryImportConfig(argv, env = process.env) {
     .filter(Boolean);
 
   return {
+    credential: env.PRISMER_API_KEY?.trim() || '',
     sourceRoot,
     excludes,
     cloudBin: env.PRISMER_CLOUD_BIN?.trim() || 'cloud',
@@ -163,6 +164,7 @@ function sourceRevision(config, directories) {
       for (const entry of readdirSync(current, { withFileTypes: true })) {
         if (entry.name.startsWith('.')) continue;
         const absolute = resolve(current, entry.name);
+        if (entry.isSymbolicLink()) throw new LibraryImportError('local_validation', 'SYMLINK_RESOURCE', 'Bundle resources must not be symlinks', 2);
         if (entry.isDirectory()) visit(absolute);
         else files.push(absolute);
       }
@@ -184,6 +186,7 @@ function bundleManifest(directory) {
     for (const entry of readdirSync(current, { withFileTypes: true })) {
       if (entry.name.startsWith('.')) continue;
       const absolute = resolve(current, entry.name);
+      if (entry.isSymbolicLink()) throw new LibraryImportError('local_validation', 'SYMLINK_RESOURCE', 'Bundle resources must not be symlinks', 2);
       if (entry.isDirectory()) visit(absolute);
       else if (!BUNDLE_EXCLUDED_FILES.has(entry.name)) files.push(absolute);
     }
@@ -249,7 +252,8 @@ function parseJsonOutput(result, stage) {
 function defaultRunCloud(config, args) {
   const result = spawnSync(config.cloudBin, args, {
     encoding: 'utf8',
-    env: { ...process.env, PRISMER_CLOUD_BASE: config.baseUrl },
+    env: { ...process.env, PRISMER_CLOUD_BASE: config.baseUrl, PRISMER_API_KEY: config.credential },
+    timeout: 120_000,
     shell: false,
   });
   if (result.error) {
@@ -270,7 +274,7 @@ function defaultRunCloud(config, args) {
 
 function writeLedger(path, ledger) {
   mkdirSync(dirname(path), { recursive: true });
-  const temporary = `${path}.tmp`;
+  const temporary = `${path}.${process.pid}.tmp`;
   writeFileSync(temporary, `${JSON.stringify(ledger, null, 2)}\n`, { mode: 0o600 });
   renameSync(temporary, path);
 }
@@ -296,13 +300,27 @@ function safeCliFailure(result) {
 }
 
 export async function runLibraryImport(config, runCloud = defaultRunCloud) {
+  if (!config.credential) throw new LibraryImportError('local_validation', 'IDENTITY_REQUIRED', 'PRISMER_API_KEY is required to bind the ledger to the executing credential', 2);
+  mkdirSync(dirname(config.ledgerPath), { recursive: true });
+  const lockPath = `${config.ledgerPath}.lock`;
+  const lock = openSync(lockPath, 'wx', 0o600);
+  try {
+    return await runLibraryImportLocked(config, runCloud);
+  } finally {
+    closeSync(lock);
+    unlinkSync(lockPath);
+  }
+}
+
+async function runLibraryImportLocked(config, runCloud) {
+  const targetBinding = sha256(JSON.stringify([config.baseUrl, config.credential]));
   const directories = discoverSkillDirectories(config);
   if (directories.length === 0) {
     throw new LibraryImportError('local_validation', 'NO_SKILLS_FOUND', 'no root SKILL.md directories found', 2);
   }
   const revision = sourceRevision(config, directories);
   const previous = readLedger(config.ledgerPath);
-  if (previous && (previous.sourceRoot !== config.sourceRoot || previous.sourceRevision !== revision)) {
+  if (previous && (previous.targetBinding !== targetBinding || previous.sourceRoot !== config.sourceRoot || previous.sourceRevision !== revision)) {
     throw new LibraryImportError(
       'local_validation',
       'IMPORT_LEDGER_CONFLICT',
@@ -350,6 +368,7 @@ export async function runLibraryImport(config, runCloud = defaultRunCloud) {
   }
 
   const ledger = {
+    targetBinding,
     schemaVersion: 1,
     sourceRoot: config.sourceRoot,
     sourceRevision: revision,
@@ -370,8 +389,12 @@ export async function runLibraryImport(config, runCloud = defaultRunCloud) {
   if (config.preflightOnly) return ledger;
 
   for (const row of rows) {
-    if (row.stage === 'verified') continue;
     const directory = resolve(config.sourceRoot, row.sourcePath);
+    if (row.stage === 'verified') {
+      const current = await readbackOwnedBundle(config, row, directory, runCloud, row.canonicalSlug);
+      if (!current.ok) { row.stage = 'readback_failed'; row.error = current.error; }
+      continue;
+    }
     const created = await runCloud(config, ['skill', 'create', directory, '--json']);
     if (!created.ok) {
       // A process may die after the server commits but before the ledger records