Skill Tracer
Skills › Compound Engineering › ce-compound › report.md

report.md

115 lines · skills/ce-compound/references/report.md at 3449230

Open on GitHub

Most marks come from matching words in the file, so treat them as pointers.

1# Completion reports
2

Completion reports

Raw lines 1 to 2
3## Success Output
4
5**User-runnable refresh rendering.** The reports below print a `ce-compound-refresh` invocation for the user to copy. Default to `/ce-compound-refresh <scope>`; use `$ce-compound-refresh <scope>` only when the active host is Codex or explicitly documents dollar-prefixed skill invocation. Render only the invocation as inline code and output one form only.
6

Success Output

User-runnable refresh rendering. The reports below print a ce-compound-refresh invocation for the user to copy. Default to /ce-compound-refresh <scope>; use $ce-compound-refresh <scope> only when the active host is Codex or explicitly documents dollar-prefixed skill invocation. Render only the invocation as inline code and output one form only.

Raw lines 3 to 6
Names a skill ce-compound-refresh :5
7### Non-interactive mode
8
9Emit a structured terminal report as the last thing this skill writes. No "What's next?" question, no blocking prompt. The report ends this skill, not the turn. When a caller invoked this skill, its next step follows the report in the same session; otherwise end the turn. End with `Documentation complete` as the terminal signal so callers can detect completion.
11For `depth:lightweight`, use this lower-overhead report after the Lightweight Mode workflow:
13```
14✓ Documentation complete (non-interactive lightweight mode)
16File: <root>/solutions/<category>/<filename>.md (created | updated)
17Track: <bug | knowledge>
18Category: <category>
19Grounding: <mechanical check clean | N flags adjudicated>
20Discoverability: <no gap | gap noted — instruction-file tip emitted | not applicable — no active project instructions>
21CONCEPTS.md: <not present | scanned, no qualifying terms | updated — N added, N refined, N folded, N scrubbed>
22CONCEPTS.md discoverability: <not checked — CONCEPTS.md unchanged | no gap | gap noted — instruction-file tip emitted | not applicable — no active project instructions>
23Refresh recommendation: <none | scope hint for /ce-compound-refresh>
25Documentation complete
26```
28For `depth:full` or backward-compatible non-interactive calls with no depth token, use the Full report:
30```
31✓ Documentation complete (non-interactive mode)
33File: <root>/solutions/<category>/<filename>.md (created | updated)
34Track: <bug | knowledge>
35Category: <category>
36Overlap: <none | low | moderate — see <path> | high — existing doc updated>
37Grounding: <clean | N flags adjudicated (X fixed, Y annotated, Z confirmed) | N claims softened or corrected | degraded — merge-state claims unverified offline>
38Instruction-file edit: <none needed | gap noted, not applied>
39CONCEPTS.md: <scanned, no qualifying terms | created with N entries (M seeded from the learning's area) | updated — N added, N refined, N folded, N scrubbed>
40Refresh recommendation: <none | scope hint for /ce-compound-refresh>
42Documentation complete
43```
45When no doc was written (e.g., non-interactive invoked on a session where the problem is not yet solved), emit a structured failure instead and end with `Documentation skipped` so callers can distinguish success from no-op:
47```
48✗ Documentation skipped (non-interactive mode)
50Reason: <one-sentence explanation — e.g., "no solved problem detected in
51conversation history" or "solution not yet verified">
53Documentation skipped
54```

Non-interactive mode

Emit a structured terminal report as the last thing this skill writes. No "What's next?" question, no blocking prompt. The report ends this skill, not the turn. When a caller invoked this skill, its next step follows the report in the same session; otherwise end the turn. End with Documentation complete as the terminal signal so callers can detect completion.

For depth:lightweight, use this lower-overhead report after the Lightweight Mode workflow:

✓ Documentation complete (non-interactive lightweight mode)

File: <root>/solutions/<category>/<filename>.md  (created | updated)
Track: <bug | knowledge>
Category: <category>
Grounding: <mechanical check clean | N flags adjudicated>
Discoverability: <no gap | gap noted — instruction-file tip emitted | not applicable — no active project instructions>
CONCEPTS.md: <not present | scanned, no qualifying terms | updated — N added, N refined, N folded, N scrubbed>
CONCEPTS.md discoverability: <not checked — CONCEPTS.md unchanged | no gap | gap noted — instruction-file tip emitted | not applicable — no active project instructions>
Refresh recommendation: <none | scope hint for /ce-compound-refresh>

Documentation complete

For depth:full or backward-compatible non-interactive calls with no depth token, use the Full report:

✓ Documentation complete (non-interactive mode)

File: <root>/solutions/<category>/<filename>.md  (created | updated)
Track: <bug | knowledge>
Category: <category>
Overlap: <none | low | moderate — see <path> | high — existing doc updated>
Grounding: <clean | N flags adjudicated (X fixed, Y annotated, Z confirmed) | N claims softened or corrected | degraded — merge-state claims unverified offline>
Instruction-file edit: <none needed | gap noted, not applied>
CONCEPTS.md: <scanned, no qualifying terms | created with N entries (M seeded from the learning's area) | updated — N added, N refined, N folded, N scrubbed>
Refresh recommendation: <none | scope hint for /ce-compound-refresh>

Documentation complete

When no doc was written (e.g., non-interactive invoked on a session where the problem is not yet solved), emit a structured failure instead and end with Documentation skipped so callers can distinguish success from no-op:

✗ Documentation skipped (non-interactive mode)

Reason: <one-sentence explanation — e.g., "no solved problem detected in
conversation history" or "solution not yet verified">

Documentation skipped
Raw lines 7 to 55
56### Interactive mode
58```
59✓ Documentation complete
61Ran Full mode.
62Auto memory: 2 relevant entries used as supplementary evidence
64Research Results:
65 ✓ Classified: performance_issue in background_job (component from corpus), category: performance-issues/
66 ✓ Drafted: 3 code fixes, prevention strategies
67 ✓ Related Docs Finder: 2 related issues
68 ✓ Session History: 3 prior sessions on same branch, 2 failed approaches surfaced
70Grounding Validation:
71 ✓ Mechanical check: 14 paths, 2 SHAs, 3 links checked — 1 flag annotated as historical
72 ✓ Semantic validator: 9 claims verified, 1 merge-state claim softened to pending
74Specialized Agent Reviews (Auto-Triggered):
75 ✓ performance-oracle: Validated query optimization approach
76 ✓ Code simplification review: Code examples are appropriately minimal
78Files written:
79- <root>/solutions/performance-issues/n-plus-one-brief-generation.md (created)
80- CONCEPTS.md (created with 3 entries: BriefSystem, EmailQueue, Brief Status)
82This documentation will be searchable for future reference when similar
83issues occur in the Email Processing or Brief System modules.
85Refresh recommendation: none
86```
88`Files written:` lists the destination the assembly step settled on. That is a pack rule's path (`<pack dir>/<file>.md`) when the user routed the capture into a writable pack, and the `<root>/solutions/` path otherwise.
90**The summary is the last thing this skill writes. When a caller invoked this skill, its next step follows the summary in the same session; otherwise end the turn. `ce-compound` does not present a "What's next?" menu.** The doc is written and any cross-references the workflow found are already in it. Cross-doc maintenance (fixing references in *other* docs, consolidation) is left to `ce-compound-refresh`, the skill designed for it, through the `Refresh recommendation` line above. It is not applied here, because that would edit tracked docs beyond the one deliverable. If the user wants to view the file or take a follow-up action, they will ask. (Interactive mode only.)
92**Alternate interactive output (when updating an existing doc due to high overlap):** in non-interactive mode, this case is communicated via the `Overlap: high — existing doc updated` line of the non-interactive terminal report above, not as a separate output block.
94```
95✓ Documentation updated (existing doc refreshed with current context)
97Overlap detected: <root>/solutions/performance-issues/n-plus-one-queries.md
98 Matched dimensions: problem statement, root cause, solution, referenced files
99 Action: Updated existing doc with fresher code examples and prevention tips
101File updated:
102- <root>/solutions/performance-issues/n-plus-one-queries.md (added last_updated: 2026-03-24)
103```

Interactive mode

✓ Documentation complete

Ran Full mode.
Auto memory: 2 relevant entries used as supplementary evidence

Research Results:
  ✓ Classified: performance_issue in background_job (component from corpus), category: performance-issues/
  ✓ Drafted: 3 code fixes, prevention strategies
  ✓ Related Docs Finder: 2 related issues
  ✓ Session History: 3 prior sessions on same branch, 2 failed approaches surfaced

Grounding Validation:
  ✓ Mechanical check: 14 paths, 2 SHAs, 3 links checked — 1 flag annotated as historical
  ✓ Semantic validator: 9 claims verified, 1 merge-state claim softened to pending

Specialized Agent Reviews (Auto-Triggered):
  ✓ performance-oracle: Validated query optimization approach
  ✓ Code simplification review: Code examples are appropriately minimal

Files written:
- <root>/solutions/performance-issues/n-plus-one-brief-generation.md (created)
- CONCEPTS.md (created with 3 entries: BriefSystem, EmailQueue, Brief Status)

This documentation will be searchable for future reference when similar
issues occur in the Email Processing or Brief System modules.

Refresh recommendation: none

Files written: lists the destination the assembly step settled on. That is a pack rule's path (<pack dir>/<file>.md) when the user routed the capture into a writable pack, and the <root>/solutions/ path otherwise.

**The summary is the last thing this skill writes. When a caller invoked this skill, its next step follows the summary in the same session; otherwise end the turn. ce-compound does not present a "What's next?" menu.** The doc is written and any cross-references the workflow found are already in it. Cross-doc maintenance (fixing references in other docs, consolidation) is left to ce-compound-refresh, the skill designed for it, through the Refresh recommendation line above. It is not applied here, because that would edit tracked docs beyond the one deliverable. If the user wants to view the file or take a follow-up action, they will ask. (Interactive mode only.)

Alternate interactive output (when updating an existing doc due to high overlap): in non-interactive mode, this case is communicated via the Overlap: high — existing doc updated line of the non-interactive terminal report above, not as a separate output block.

✓ Documentation updated (existing doc refreshed with current context)

Overlap detected: <root>/solutions/performance-issues/n-plus-one-queries.md
  Matched dimensions: problem statement, root cause, solution, referenced files
  Action: Updated existing doc with fresher code examples and prevention tips

File updated:
- <root>/solutions/performance-issues/n-plus-one-queries.md (added last_updated: 2026-03-24)
Raw lines 56 to 104
Names a skill ce-compound-refresh :90
105## Common Mistakes to Avoid
107| ❌ Wrong | ✅ Correct |
108|----------|-----------|
109| Subagents write product files into `docs/` or edit tracked paths | Subagents write only scratch artifacts under `<run-dir>/` and return the path; orchestrator writes the one final doc |
110| Subagent returns a long prose body only as its inline response | Subagent writes full output to its run artifact; orchestrator Reads it back (inline return is fallback only) |
111| Research and assembly run in parallel | Research completes → then assembly runs |
112| Non-interactive Discoverability Check edits AGENTS.md/CLAUDE.md | non-interactive Full reports `Instruction-file edit: gap noted, not applied`; non-interactive Lightweight emits a discoverability tip; only interactive Full applies the edit after consent |
113| Creating a new doc when an existing doc covers the same problem | Check overlap assessment; update the existing doc when overlap is high |
114| Asserting code behavior or merge-state from conversation memory | Read the defining source line before asserting; cite PR numbers over SHAs; soften unverifiable claims (Phase 1 extractor rules, re-checked in Phase 2.45) |
115| Batching several learnings through one run and stitching cross-references between drafts | One learning per run; run the skill sequentially for each additional learning |

Common Mistakes to Avoid

❌ Wrong✅ Correct
Subagents write product files into docs/ or edit tracked pathsSubagents write only scratch artifacts under <run-dir>/ and return the path; orchestrator writes the one final doc
Subagent returns a long prose body only as its inline responseSubagent writes full output to its run artifact; orchestrator Reads it back (inline return is fallback only)
Research and assembly run in parallelResearch completes → then assembly runs
Non-interactive Discoverability Check edits AGENTS.md/CLAUDE.mdnon-interactive Full reports Instruction-file edit: gap noted, not applied; non-interactive Lightweight emits a discoverability tip; only interactive Full applies the edit after consent
Creating a new doc when an existing doc covers the same problemCheck overlap assessment; update the existing doc when overlap is high
Asserting code behavior or merge-state from conversation memoryRead the defining source line before asserting; cite PR numbers over SHAs; soften unverifiable claims (Phase 1 extractor rules, re-checked in Phase 2.45)
Batching several learnings through one run and stitching cross-references between draftsOne learning per run; run the skill sequentially for each additional learning
Raw lines 105 to 115
Starts an agent Subagents :109
Starts an agent Subagent :110
Project instruction file AGENTS.md :112
Project instruction file CLAUDE.md :112