Individual skill
ce-compound
Document a solved problem as a durable repo learning. Use when verified work produced non-obvious reasoning absent from its final code, tests, or existing docs; avoid routine fixes whose artifacts already explain the lesson.
skills/ce-compound/SKILL.md
Source commit 3449230705a508229a5a298671e9031e489f0278
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 2, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 25,965
- Repository last updated
- Nov 7, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- compound Repository topic
- engineering Repository topic
- education Derived category
- docs Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 7,901 bytesSKILL.mdcore · 7,901 bytesassets/resolution-template.mddoc · 2,842 bytesreferences/agents/best-practices-researcher.mddoc · 7,302 bytesreferences/agents/data-integrity-guardian.mddoc · 3,216 bytesreferences/agents/framework-docs-researcher.mddoc · 5,551 bytesreferences/agents/pattern-recognition-specialist.mddoc · 3,675 bytesreferences/agents/performance-oracle.mddoc · 4,588 bytesreferences/agents/security-sentinel.mddoc · 4,159 bytesreferences/agents/session-historian.mddoc · 7,078 bytesreferences/assembly.mddoc · 16,742 bytesreferences/concepts-vocabulary.mddoc · 9,033 bytesreferences/enhancement.mddoc · 2,738 bytesreferences/grounding-validation.mddoc · 7,326 bytesreferences/lightweight.mddoc · 6,988 bytesreferences/modes.mddoc · 1,818 bytesreferences/refresh-and-discoverability.mddoc · 9,836 bytesreferences/report.mddoc · 6,997 bytesreferences/research.mddoc · 14,599 bytesreferences/schema.yamlasset · 9,756 bytesreferences/session-history.mddoc · 9,243 bytesreferences/yaml-schema.mddoc · 9,203 bytesscripts/packs-resolve.pyruns · 31,561 bytesscripts/session-history/discover-sessions.shruns · 11,345 bytesscripts/session-history/extract-errors.pyruns · 9,270 bytesscripts/session-history/extract-metadata.pyruns · 20,599 bytesscripts/session-history/extract-skeleton.pyruns · 21,932 bytesscripts/validate-doc-claims.pyruns · 20,561 bytesscripts/validate-frontmatter.pyruns · 5,060 bytes
Read excerpt
# /ce-compound
**Outcome:** one qualifying solved problem is written as a durable learning under `<root>/solutions/`, grounded against the current tree, discoverable by the next agent.
**Done:** a qualifying doc is written or updated, its frontmatter and claims validated, vocabulary capture recorded, and the mode's completion report emitted; when no learning qualifies, nothing is written and the report says why.
**One learning per run.** A session that produced several gets several sequential runs, never one batched run. Read `references/research.md`; it explains what batching breaks.
## Preconditions
Document only a problem that is solved and verified.
<!-- ce-durable-bar:start -->