@cleocode/skills 2026.9.21 → 2026.9.23

package/skills/{ct-skill-validator/SKILL.md → ct-skill-author/references/validating.md}

@@ -1,14 +1,4 @@
----
-name: ct-skill-validator
-description: Validates an existing skill folder against the full CLEO standard and ecosystem. Use when auditing skills for structural compliance, verifying a skill fits into the CLEO ecosystem and constitution, running quality A/B evals, or preparing a skill for distribution. Runs a 3-phase validation loop — structural, ecosystem fit, and quality eval — then presents all findings as an HTML report opened in the user's browser. Iterates until all required phases pass.
-disable-model-invocation: true
-allowed-tools: Bash(python *)
-metadata:
-  version: 1.0.0
-  tier: internal
-  install: internal
-  stability: deprecated
----
+<!-- Merged from the ct-skill-validator skill into ct-skill-author (T12649, D11157). -->
 
 # CLEO Skill Validator
 
@@ -31,7 +21,7 @@ python ${CLAUDE_SKILL_DIR}/scripts/validate.py <skill-dir>
 
 # With manifest checks (Tier 4):
 python ${CLAUDE_SKILL_DIR}/scripts/validate.py <skill-dir> \
-  --manifest <manifest.json> --dispatch-config <dispatch-config.json>
+  --manifest packages/skills/skills/manifest.json
 
 # JSON output (for scripting):
 python ${CLAUDE_SKILL_DIR}/scripts/validate.py <skill-dir> --json
@@ -40,7 +30,10 @@ python ${CLAUDE_SKILL_DIR}/scripts/validate.py <skill-dir> --json
 python ${CLAUDE_SKILL_DIR}/scripts/audit_body.py <skill-dir>
 
 # Manifest alignment check: bundled into validate.py Tier 4. Use:
-#   python validate.py <skill-dir> --manifest <manifest.json> --dispatch-config <dispatch-config.json>
+#   python validate.py <skill-dir> --manifest packages/skills/skills/manifest.json
+# (CLEO's own package ships no dispatch-config.json or provider-skills-map.json
+# since T12649/T12679; --dispatch-config/--provider-map only apply to external
+# libraries that still ship them. For CLEO skills, gates 29-32 are authoritative.)
 
 # Progressive-disclosure depth check (T9684 — CI gate):
 python ${CLAUDE_SKILL_DIR}/scripts/check_depth.py <skill-dir>
@@ -61,7 +54,7 @@ python ${CLAUDE_SKILL_DIR}/scripts/check_depth.py <skill-dir> --audit-allowlist
 
 Pre-existing stubs are allowlisted with follow-up task IDs in
 `scripts/check_depth.py::ALLOWLIST`. Gold-standard skills:
-`ct-orchestrator` (9 refs) and `ct-skill-creator` (7 refs).
+`ct-orchestrator` (9 refs) and `ct-skill-author` (7 refs).
 
 **Allowlist hygiene:** every entry carries `last_reviewed: YYYY-MM-DD HH:MM:SS`.
 `check_depth.py` runs a silent background audit on every invocation and emits
@@ -80,8 +73,8 @@ Repeat until errors = 0. Do not proceed to Phase 2 while errors remain.
 - Tier 1 — Structure: SKILL.md exists, frontmatter parseable, no CLEO-only fields
 - Tier 2 — Frontmatter Quality: name matches dir, description has trigger indicators
 - Tier 3 — Body Quality: length, no placeholder text, file references exist on disk
-- Tier 4 — CLEO Integration: manifest and dispatch-config alignment (optional)
-- Tier 5 — Provider Compatibility: provider-skills-map check (optional)
+- Tier 4 — CLEO Integration: manifest alignment (dispatch-config only for external libraries that ship one)
+- Tier 5 — Provider Compatibility: provider-skills-map check (external libraries only; CLEO removed its map in T12679)
 
 See [references/validation-rules.md](references/validation-rules.md) for full rule set.
 
@@ -135,11 +128,11 @@ Repeat until verdict is `PASS` or `PASS_WITH_WARNINGS`. WARN is acceptable; ERRO
 ## Phase 3: Quality A/B Eval
 
 Tests whether the skill actually improves agent output quality vs. no skill context.
-Phase 3 is **delegated** — `ct-skill-validator` does static analysis; runtime
+Phase 3 is **delegated** — `ct-skill-author` does static analysis; runtime
 quality evals live in a dedicated skill (`skill-evaluator` preferred,
-`ct-skill-creator` as legacy fallback).
+`ct-skill-author` as legacy fallback).
 
-> **Scope boundary:** `ct-skill-validator` is *static* — it checks structure,
+> **Scope boundary:** `ct-skill-author` is *static* — it checks structure,
 > frontmatter, body, manifest, depth, ecosystem fit. For deep runtime A/B
 > benchmarking, regression detection, and auto-improvement, the dispatcher
 > below routes to `skill-evaluator`, which owns that workflow end-to-end.
@@ -182,7 +175,7 @@ loop: generate → run → grade → aggregate → analyze → detect-regression
 propose. See `skill-evaluator/SKILL.md` for the workflow it actually
 executes.
 
-When `ct-skill-creator` is the resolved fallback, the wrapper invokes its
+When `ct-skill-author` is the resolved fallback, the wrapper invokes its
 `run_eval.py` with the same arguments translated to its CLI shape.
 
 ### Manual A/B (if you want to drive runs yourself)
@@ -233,7 +226,7 @@ Open the report in the browser: omit `--no-open` (default behaviour opens browse
 
 ## Self-Validation
 
-This skill validates itself. To validate ct-skill-validator:
+This skill validates itself. To validate ct-skill-author:
 
 ```bash
 python ${CLAUDE_SKILL_DIR}/scripts/validate.py ${CLAUDE_SKILL_DIR}

package/skills/{ct-skill-validator → ct-skill-author}/references/validation-rules.md

@@ -9,8 +9,8 @@ The CLEO Skill Validator enforces compliance across five tiers of increasing dep
 1. **Structure** — Does the skill have the required files and valid frontmatter?
 2. **Frontmatter Quality** — Are all frontmatter fields correct, well-formed, and non-contradictory?
 3. **Body Quality** — Is the body content complete, concise, and free of placeholders?
-4. **CLEO Integration** — Does the skill align with manifest.json and dispatch-config.json?
-5. **Provider Compatibility** — Is the skill referenced in the provider-skills-map?
+4. **CLEO Integration** — Does the skill align with manifest.json (and dispatch-config.json, for external libraries that ship one)?
+5. **Provider Compatibility** — Is the skill referenced in the provider-skills-map (external libraries only; CLEO's was removed in T12679)?
 
 Tiers 1-3 run on every validation. Tiers 4-5 are opt-in via CLI flags.
 

package/skills/{ct-skill-validator → ct-skill-author}/scripts/_skill_finder.py

@@ -109,7 +109,7 @@ def _candidates(name: str, caller_skill_dir: Path) -> Iterator[Path]:
     #      - <child>/skills/<name>
     #      - <child>/packages/skills/skills/<name>
     #    This finds skills under sibling project roots — e.g. when the
-    #    caller is in /mnt/projects/cleocode/.../ct-skill-validator/ and
+    #    caller is in /mnt/projects/cleocode/.../ct-skill-author/ and
     #    the target is in /mnt/projects/proxmox/skills/<name>/. The walk
     #    eventually reaches the common ancestor /mnt/projects/ where both
     #    cleocode and proxmox are children. Bounded by MAX_SIBLINGS per
@@ -176,7 +176,7 @@ def find_skill(name: str, *, caller: Path | None = None) -> Path | None:
 def find_first(names: list[str], *, caller: Path | None = None) -> tuple[str, Path] | None:
     """Return the (name, path) of the first found skill from a preference list.
 
-    Lets callers say "prefer skill-evaluator, fall back to ct-skill-creator"
+    Lets callers say "prefer skill-evaluator, fall back to ct-skill-author"
     without hardcoding either path.
     """
     for n in names:

package/skills/{ct-skill-validator → ct-skill-author}/scripts/check_depth.py

@@ -5,7 +5,7 @@ CLEO Skill Depth Check — progressive-disclosure-depth rule (T9684).
 Fails when a skill's SKILL.md is below the depth threshold AND it has
 no references/ subdir with at least the manifest-declared reference
 files. The gold standard is ct-orchestrator (9 references) and
-ct-skill-creator (7 references); the rule is calibrated to flag
+ct-skill-author (7 references); the rule is calibrated to flag
 stubs without forcing every skill to that depth.
 
 Rule logic:
@@ -41,7 +41,7 @@ from pathlib import Path
 # Adjust here, then re-run the audit to verify all 19 active skills pass.
 MIN_BODY_LINES = 100
 MIN_REF_FILES = 3
-GOLD_STANDARDS = ("ct-orchestrator", "ct-skill-creator")
+GOLD_STANDARDS = ("ct-orchestrator", "ct-skill-author")
 
 # Cadence for the allowlist audit — entries older than this are flagged stale.
 ALLOWLIST_STALE_DAYS = 30
@@ -62,9 +62,6 @@ LAST_REVIEWED_RE = re.compile(r"last_reviewed:\s*(\d{4}-\d{2}-\d{2} \d{2}:\d{2}:
 # Format: skill-name -> "task-id: rationale | last_reviewed: YYYY-MM-DD HH:MM:SS"
 ALLOWLIST: dict[str, str] = {
     "ct-codebase-mapper": "T9567-followup: pre-existing; depth-backfill deferred | last_reviewed: 2026-05-21 14:00:18",
-    "ct-master-tac":      "T9567-followup: pre-existing; depth-backfill deferred | last_reviewed: 2026-05-21 14:00:18",
-    "ct-memory":          "T9567-followup: pre-existing; depth-backfill deferred | last_reviewed: 2026-05-21 14:00:18",
-    "ct-stickynote":      "T9567-followup: ephemeral note skill; minimal-by-design | last_reviewed: 2026-05-21 14:00:18",
 }
 
 

package/skills/{ct-skill-validator → ct-skill-author}/scripts/generate_validation_report.py

@@ -344,7 +344,7 @@ def generate_html(
     {grading_html}
     {comparison_html}
 
-    <div class="footer">Generated by ct-skill-validator &mdash; CLEO Full Validation Report</div>
+    <div class="footer">Generated by ct-skill-author &mdash; CLEO Full Validation Report</div>
 </body>
 </html>
 """

package/skills/{ct-skill-validator → ct-skill-author}/scripts/run_quality_eval.py

@@ -31,7 +31,7 @@ from _skill_finder import find_first  # noqa: E402
 
 # Preference order — first found wins. Lets the user opt-in to a different
 # eval skill via $SKILL_FINDER_PATH without code changes.
-PREFERENCE = ["skill-evaluator", "ct-skill-creator"]
+PREFERENCE = ["skill-evaluator", "ct-skill-author", "ct-skill-creator"]
 
 
 def main() -> int:
@@ -83,7 +83,7 @@ def main() -> int:
         if args.executor:
             cmd += ["--executor", args.executor]
     else:
-        # ct-skill-creator legacy paths
+        # ct-skill-author (formerly ct-skill-creator) eval paths
         if args.trigger:
             script = eval_skill_path / "scripts" / "run_eval.py"
             cmd = ["python3", str(script), "--skill-path", str(target_skill)]

package/skills/ct-spec-writer/SKILL.md

@@ -1,11 +1,8 @@
 ---
 name: ct-spec-writer
 description: Technical specification writing using RFC 2119 language for clear, unambiguous requirements. Creates protocol specifications, technical requirements, API specifications, and architecture documents with testable requirements and compliance criteria. Use when writing specifications, defining protocols, documenting requirements, or creating API contracts. Triggers on specification tasks, protocol definition needs, or requirement documentation.
-version: 2.1.0
-core: false
-category: recommended
+version: 2.1.2
 protocol: specification
-loomStage: specification
 adrRefs:
   - ADR-014
   - ADR-023
@@ -20,9 +17,14 @@ compatibility:
   - gemini-cli
 license: MIT
 metadata:
-  version: 2.1.0
+  version: 2.1.2
   tier: on-demand
   install: harness
+  covers:
+    - packages/core/src/validation/protocols/cant/specification.cant
+    - packages/core/src/validation/protocols/protocols-markdown/specification.md
+  loomStage: specification
+  lastReviewed: 2026-09-28
   stability: stable
 ---
 
@@ -229,7 +231,7 @@ Spec blobs live in the docs SSoT; published copies on disk go in
 1. Read task: `{{TASK_SHOW_CMD}} {{TASK_ID}}`
 2. Start task: `{{TASK_START_CMD}} {{TASK_ID}}` (if not already started by orchestrator)
 3. Write specification to `docs/specs/{{SPEC_NAME}}.md`
-4. Append manifest entry to `{{MANIFEST_PATH}}`
+4. Record the manifest entry: `cleo manifest append --task {{TASK_ID}} --type specification --content "<one-paragraph summary>"`
 5. Complete task: `{{TASK_COMPLETE_CMD}} {{TASK_ID}}`
 6. Return summary message
 
@@ -242,7 +244,7 @@ Spec blobs live in the docs SSoT; published copies on disk go in
 ### Output Requirements
 
 1. MUST write specification to: `docs/specs/{{SPEC_NAME}}.md`
-2. MUST append ONE line to: `{{MANIFEST_PATH}}`
+2. MUST record ONE manifest entry: `cleo manifest append --entry '<entry JSON>'` (the flat manifest file is retired, ADR-027)
 3. MUST return ONLY: "Specification complete. Manifest appended to pipeline_manifest."
 4. MUST NOT return specification content in response
 

package/skills/ct-task-executor/SKILL.md

@@ -1,11 +1,8 @@
 ---
 name: ct-task-executor
 description: General implementation task execution for completing assigned CLEO tasks by following instructions and producing concrete deliverables. Handles coding, configuration, documentation work with quality verification against acceptance criteria and progress reporting. Use when executing implementation tasks, completing assigned work, or producing task deliverables. Triggers on implementation tasks, general execution needs, or task completion work.
-version: 2.7.0
-core: true
-category: core
+version: 2.7.3
 protocol: implementation
-loomStage: implementation
 adrRefs:
   - ADR-070
   - ADR-062
@@ -20,10 +17,16 @@ compatibility:
   - gemini-cli
 license: MIT
 metadata:
-  version: 2.7.0
+  version: 2.7.3
   tier: core
   install: harness
-  lastReviewed: 2026-09-19
+  covers:
+    - packages/cleo/src/cli/commands/verify.ts
+    - packages/cleo/src/cli/commands/complete.ts
+    - packages/core/src/validation/protocols/cant/implementation.cant
+    - packages/core/src/validation/protocols/protocols-markdown/implementation.md
+  loomStage: implementation
+  lastReviewed: 2026-09-28
   stability: stable
 ---
 
@@ -96,8 +99,8 @@ Context injection for implementation tasks spawned via cleo-subagent. Provides d
 2. Focus already set by orchestrator (set if working standalone)
 3. Execute instructions (see Methodology below)
 4. Verify deliverables against acceptance criteria
-5. Write output: `{{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md`
-6. Append manifest: `{{MANIFEST_PATH}}`
+5. Record output: `cleo docs add {{TASK_ID}} --content - --type note --slug {{TOPIC_SLUG}}`
+6. Record the manifest entry: `cleo manifest append --task {{TASK_ID}} --type implementation --content "<one-paragraph summary>"`
 7. Complete task: `{{TASK_COMPLETE_CMD}} {{TASK_ID}}`
 8. Return summary message
 
@@ -156,8 +159,8 @@ The routing prints a one-line info message to stderr (suppress with
 
 ### Output Requirements
 
-1. MUST write findings to: `{{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md`
-2. MUST append ONE line to: `{{MANIFEST_PATH}}`
+1. MUST record findings with `cleo docs add {{TASK_ID}} --content - --type note --slug {{TOPIC_SLUG}}` (never a raw file under `.cleo/agent-outputs/`)
+2. MUST record ONE manifest entry: `cleo manifest append --entry '<entry JSON>'` (the flat manifest file is retired, ADR-027)
 3. MUST return ONLY: "Implementation complete. Manifest appended to pipeline_manifest."
 4. MUST NOT return implementation details in response
 
@@ -165,7 +168,7 @@ The routing prints a one-line info message to stderr (suppress with
 
 ## Output File Format
 
-Write to `{{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md`:
+Record it with `cleo docs add {{TASK_ID}} --content - --type note --slug {{TOPIC_SLUG}}`, using this body:
 
 ```markdown
 # {{TASK_NAME}}
@@ -190,7 +193,7 @@ Write to `{{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md`:
 
 ## Acceptance Criteria Verification
 
-Record each criterion's changed artifacts and actual verification results. A merged PR with green CI provides provenance; it cannot automatically satisfy implementation, testing and review. Use `pr:<number>;files:<changed-path>` for implementation and actual result atoms for test/review gates, with explicit `satisfies:T1234#AC1` links for canonical criteria. The PR must relate to the task; documentation-only changes cannot prove a code fix. Research and documentation tasks may use appropriately scoped documentary evidence. Fetch the merge commit before claiming its artifact bytes were inspected. Criterion edits require fresh evidence. A completed child does not establish that its parent's independent criteria were met.
+Record each criterion's changed artifacts and actual verification results. A merged PR with green CI provides provenance; it cannot automatically satisfy implementation, testing and review. Use `pr:<number>;files:<changed-path>` for implementation (`pr:<component>@<integration>` when your PR merged into an integration branch) and actual result atoms for test/review gates, with explicit `satisfies:T1234#AC1` links for canonical criteria. The PR must relate to the task; documentation-only changes cannot prove a code fix. Research and documentation tasks may use appropriately scoped documentary evidence. Fetch the merge commit before claiming its artifact bytes were inspected. Criterion edits require fresh evidence. A completed child does not establish that its parent's independent criteria were met.
 
 
 | Criterion | Status | Notes |
@@ -213,7 +216,7 @@ Record each criterion's changed artifacts and actual verification results. A mer
 
 ## Manifest Entry Format
 
-Append ONE entry via `cleo manifest append <json>` (writes to pipeline_manifest table per ADR-027):
+Append ONE entry via `cleo manifest append --entry '<json>'` (writes to pipeline_manifest table per ADR-027):
 
 ```json
 {"id":"{{TOPIC_SLUG}}-{{DATE}}","file":"{{DATE}}_{{TOPIC_SLUG}}.md","title":"{{TASK_NAME}}","date":"{{DATE}}","status":"complete","agent_type":"implementation","topics":{{TOPICS_JSON}},"key_findings":["Completed: deliverable 1","Completed: deliverable 2","All acceptance criteria passed"],"actionable":false,"needs_followup":[],"linked_tasks":["{{EPIC_ID}}","{{TASK_ID}}"]}
@@ -237,7 +240,7 @@ Append ONE entry via `cleo manifest append <json>` (writes to pipeline_manifest
 - [ ] All instructions executed
 - [ ] All deliverables produced
 - [ ] Acceptance criteria verified
-- [ ] Output file written to `{{OUTPUT_DIR}}/`
+- [ ] Output recorded with `cleo docs add` (slug in the return message)
 - [ ] Manifest entry appended (single line, valid JSON)
 - [ ] Task completed via `{{TASK_COMPLETE_CMD}}`
 - [ ] Session ended with summary note (if executor owns session)
@@ -304,8 +307,8 @@ cleo session list --all
 # Clean up stale sessions (72h+ inactive)
 cleo session gc
 
-# Force cleanup including active sessions (use cautiously)
-cleo session gc --include-active
+# Also end active sessions idle longer than N days (use cautiously)
+cleo session gc --max-age 1
 ```
 
 ### Best Practices

package/skills/ct-task-executor/references/common-failures.md

@@ -61,7 +61,7 @@ relate commits to the task.
 without reading ADR-062. The CLEO contract is that workers commit on
 their task branch; the integrator MUST use `git merge --no-ff
 task/<id>` to preserve SHAs, author identity, and the
-`cleo find <task-id> --commits` trace.
+`git log --grep <task-id>` trace.
 
 **Fix.** Always `git merge --no-ff task/<TID>` for integration. See
 `feedback_cherry_pick_worktrees.md` for the full pattern.

package/skills/ct-validator/SKILL.md

@@ -1,11 +1,8 @@
 ---
 name: ct-validator
 description: Compliance validation for verifying systems, documents, or code against requirements, schemas, or standards. Performs schema validation, code compliance checks, document validation, and protocol compliance verification with detailed pass/fail reporting. Use when validating compliance, checking schemas, verifying code standards, or auditing protocol implementations. Triggers on validation tasks, compliance checks, or quality verification needs.
-version: 2.0.0
-core: false
-category: recommended
+version: 2.0.4
 protocol: validation
-loomStage: validation
 adrRefs:
   - ADR-051
   - ADR-023
@@ -20,9 +17,14 @@ compatibility:
   - gemini-cli
 license: MIT
 metadata:
-  version: 2.0.0
+  version: 2.0.4
   tier: on-demand
   install: harness
+  covers:
+    - packages/core/src/validation/protocols/cant/validation.cant
+    - packages/core/src/validation/protocols/protocols-markdown/validation.md
+  loomStage: validation
+  lastReviewed: 2026-09-28
   stability: stable
 ---
 
@@ -194,8 +196,8 @@ the Validate-phase Lead prompt, listing the touched packages and the exact
 1. Read task: `{{TASK_SHOW_CMD}} {{TASK_ID}}`
 2. Start task: `{{TASK_START_CMD}} {{TASK_ID}}` (if not already started by orchestrator)
 3. Execute validation checks
-4. Write validation report to `{{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md`
-5. Append manifest entry to `{{MANIFEST_PATH}}`
+4. Record validation report with `cleo docs add {{TASK_ID}} --content - --type note --slug {{TOPIC_SLUG}}`
+5. Record the manifest entry: `cleo manifest append --task {{TASK_ID}} --type validation --content "<one-paragraph summary>"`
 6. Complete task: `{{TASK_COMPLETE_CMD}} {{TASK_ID}}`
 7. Return summary message
 
@@ -207,8 +209,8 @@ the Validate-phase Lead prompt, listing the touched packages and the exact
 
 ### Output Requirements
 
-1. MUST write validation report to: `{{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md`
-2. MUST append ONE line to: `{{MANIFEST_PATH}}`
+1. MUST record validation report with `cleo docs add {{TASK_ID}} --content - --type note --slug {{TOPIC_SLUG}}` (never a raw file under `.cleo/agent-outputs/`)
+2. MUST record ONE manifest entry: `cleo manifest append --entry '<entry JSON>'` (the flat manifest file is retired, ADR-027)
 3. MUST return ONLY: "Validation complete. Manifest appended to pipeline_manifest."
 4. MUST NOT return validation content in response
 

package/skills/ct-validator/references/compliance-reports.md

@@ -106,7 +106,7 @@ unactionable — the consumer cannot prioritize.
 ### Warnings
 
 **W-001**: `packages/cleo/src/dispatch.ts` is 487 lines (warn at 400).
-- Rule: ct-skill-validator audit_body §body-length
+- Rule: ct-skill-author audit_body §body-length
 - Fix: Extract sub-handlers into sibling files.
 - Verification: re-run audit_body.py.
 

package/skills/ct-validator/references/validation-modes.md

@@ -93,9 +93,9 @@ links; scan for placeholder text; verify formatting.
 **Tool examples.**
 
 ```bash
-# Use the ct-skill-validator scripts as a model
-python packages/skills/skills/ct-skill-validator/scripts/validate.py <skill-dir>
-python packages/skills/skills/ct-skill-validator/scripts/audit_body.py <skill-dir>
+# Use the ct-skill-author scripts as a model
+python packages/skills/skills/ct-skill-author/scripts/validate.py <skill-dir>
+python packages/skills/skills/ct-skill-author/scripts/audit_body.py <skill-dir>
 
 # Generic markdown link check
 markdown-link-check docs/specs/*.md