task-pipeline-skill 1.102.0 → 1.102.2

package/CHANGELOG.md

@@ -1,3 +1,19 @@
+## v1.102.2: v1.102.1 republished
+
+- **v1.102.1 republished.** Its tag was pushed and the release run (40241842429) refused it before
+  publishing: `docs/evidence/retro.md` → *Releases that carry no stamp* did not name v1.102.1. That
+  section now names v1.102.1 and v1.102.2, and v1.102.2 ships v1.102.1's content (the three
+  descriptions within a 300-character budget). `v1.102.1` stays as an unpublished tag.
+
+## v1.102.1: descriptions within a 300-character budget
+
+- **Descriptions within a 300-character budget** (hub board row B-255 (a)): Claude Code lists every
+  skill's description in one ~30,000-character budget, and on the operator's machine the listing
+  stood at 51,178. Measured the hub's way (whitespace collapsed, front matter only): task-pipeline
+  388 to 294, project-audit 401 to 295, evidence-docs 397 to 283. The full trigger lists stay in each
+  `## Triggers`; B-001 and the README conformance sentence carry the new figure. Release impact card:
+  `docs/evidence/specs/2026-10-25-v11021-release-impact.md`.
+
 ## v1.102.0 (2026-10-24)
 
 Guards: 530 → **531**; property checks 15 → **15**. Negative 550 is new; the release impact

package/README.md

@@ -643,7 +643,7 @@ must say so.
 ### Held to Anthropic's own Skill authoring guidance
 
 Audited against the four Agent Skills pages. Most of it already held — `name`
-13/64 chars, `description` 386/1024 chars, `SKILL.md` 207/500 lines, all 55 references
+13/64 chars, `description` 292/1024 chars, `SKILL.md` 207/500 lines, all 55 references
 reachable from `SKILL.md` through explicit reference routes, and the bundle far under the 30 MB ceiling. What
 did not, now does:
 

package/SKILL-CARD.md

@@ -12,7 +12,7 @@ harmless.
 |---|---|
 | **Purpose** | Runs a substantial task through ten gated delivery stages — intake grill, docs study, brainstorm, spec, plan, subagent build, tests, lint/deploy, post-deploy, docs+registers, acceptance — refusing to advance until each gate passes |
 | **Owner** | ssheleg ([github.com/ssheleg/task-pipeline](https://github.com/ssheleg/task-pipeline)) |
-| **Version** | 1.102.0 |
+| **Version** | 1.102.2 |
 | **Surface** | Claude Code (filesystem skill + plugin) and the vercel `skills` CLI. **Not** uploaded to the Skills API; custom Skills do not sync across surfaces |
 | **Dependencies** | None required. Optional: `context7` (MCP), `figma` (MCP), super-ux, agent-sync, graphify, obsidian-wiki, and **one of two browser channels** — `playwright` (CLI or MCP) or `chrome-devtools` (MCP); either satisfies the browser step and neither is required. The engine is WebKit (Safari) first; `chrome-devtools` is Chrome-only, a stated exception. Every stage's doctrine ships in-repo; user-facing stage 3 requires a valid scenario artifact; super-ux is preferred, with equivalent-provider and inline-fallback paths under the provider contract |
 | **Evaluation status** | Suite authored, 5 categories. One recorded run, **self-observed by the author**; **zero blind runs on zero of three models** — the split, and the numbers, live in [`evals/RESULTS.md`](evals/RESULTS.md) and are computed by `evals/run.py` |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "task-pipeline-skill",
-  "version": "1.102.0",
+  "version": "1.102.2",
   "description": "Full-cycle delivery pipeline for coding agents: a mandatory built-in intake grill, then 10 gated stages (docs, brainstorm+decompose, spec, plan, build, tests, lint/deploy, post-deploy, docs/wiki, acceptance). Every stage's doctrine ships inside the skill — no companion plugin required. This package is the installer CLI.",
   "bin": {
     "task-pipeline": "bin/task-pipeline.js"

package/plugins/task-pipeline/.claude-plugin/plugin.json

@@ -3,7 +3,7 @@
   "name": "task-pipeline",
   "displayName": "Task Pipeline",
   "description": "Runs a substantial task through a mandatory built-in intake grill, then 10 gated stages (docs, brainstorm+decompose, spec, plan, subagent build, tests, lint/deploy, post-deploy, docs/wiki, acceptance). Every stage's doctrine is built into the skill — no companion plugin required — with typed auto/judgment/manual gates, a frozen requirement spine that closes with evidence, a work board and a verification ledger that outlive a run, an exposure line naming what shipped unconfirmed, a progress rail computed from the project's own config, a proportional short path for small changes, a loop guard whose ceilings stop and record a blocker, and stage-3 tracks for what a product does, how it sounds and how it looks. Two modes need no task: `checkup` (what is unverified) and `setup` (audit existing docs); a third, `waves`, takes the whole board and closes it in waves that each finish in one pass. Retro insights can publish upstream as issues, opt-in and redacted.",
-  "version": "1.102.0",
+  "version": "1.102.2",
   "author": {
     "name": "ssheleg",
     "url": "https://x.com/sshlg93"

package/plugins/task-pipeline/skills/evidence-docs/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: evidence-docs
-description: "Use when writing or reviewing anything read as true: a decision record, ADR, README, acceptance report, runbook, changelog, audit finding, or a claim that something was verified. Applies the ten canons of evidence-backed documentation and routes to the doctrine enforcing each; also a documentation gate or decision register. Not for: drafts, chat answers, commit messages; 'без доков' opts out."
+description: "Use when writing or reviewing anything read as true: a decision record, ADR, README, acceptance report, runbook, changelog, audit finding, a claim of verification. Applies the ten canons of evidence-backed docs. Not for: drafts, chat answers, commit messages; 'без доков' opts out."
 license: MIT
 compatibility: "Doctrine runs on any agent. No bundled scripts — nothing to install and nothing to degrade."
 ---

package/plugins/task-pipeline/skills/project-audit/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: project-audit
-description: "Use when someone asks what is true of a whole project: finished, half-built, broken, unexplored ('project audit', 'аудит проекта'). Discovers the project, runs probes, reads production evidence, leaves a JSON sidecar, an HTML report on request. Read-only: proposes board rows, commits nothing. Not for: one deliverable inside a run, a diff review, a skill's construction; 'без диагностики' opts out."
+description: "Use when someone asks what is true of a whole project ('project audit', 'аудит проекта'): finished, broken, unexplored. Probes it, reads production evidence, leaves a JSON sidecar. Read-only. Not for: one deliverable in a run, a diff review, a skill's construction; 'без диагностики' opts out."
 license: MIT
 compatibility: "The collector (scripts/audit.py) needs python3 and reads committed state, so it needs git. Probes needing gh, npm, network or a browser declare it and report blind when it is absent — degraded, never silent."
 ---

package/plugins/task-pipeline/skills/task-pipeline/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: task-pipeline
-description: "Use when work changes the repository: feature, fix, bug, refactor, migration, integration, audit, PR review; фича, фикс, баг, рефактор, миграция, интеграция, аудит. Runs a substantial task through gated stages, intake grill to docs/wiki and acceptance; a small change takes a short path. 'waves'/'волнами' closes the board. Not for questions or one-line edits; 'без пайплайна' opts out."
+description: "Use when work changes the repository: feature, fix, refactor, migration, integration, audit, PR review; фича, баг, интеграция, аудит. Runs a substantial task through gated stages to acceptance; 'waves'/'волнами' closes the board. Not for questions or one-line edits; 'без пайплайна' opts out."
 license: MIT
 compatibility: "Doctrine runs on any agent. The bundled scripts need python3; the run needs git. Missing either degrades, never blocks — the graph verbs and seeded gates go unused, and the run says so."
 ---