doc-condenser
FeaturedDEPRECATED: The base model handles document condensation and summarization natively at high quality. This skill no longer provides meaningful uplift. Retained for reference only.
Install
Quality Score: 93/100
Skill Content
Details
- Author
- Mathews-Tom
- Repository
- Mathews-Tom/armory
- Created
- 7 months ago
- Last Updated
- 5 days ago
- Language
- Python
- License
- MIT
Bundled in these plugins
Similar Skills
Semantically similar based on skill content — not just same category
doc-consolidation
Harvest ephemeral agent-run reports (REPORT/ANALYSIS/AUDIT/SUMMARY, scratch notes) into canonical committed docs, then delete sources. Do NOT use to author new docs or judge prose (use documentation-and-adrs).
skill-condense
Shrink a bloated skill, rules file, or CLAUDE.md without losing any instruction. Run bare to rank which instruction files cost the most context for the least value; pass a skill name or path to condense one. Each rewrite is checked by a fresh-context reader that confirms every rule survived and will still be followed. Use for "/skill-condense", "this skill is too long", or "trim my CLAUDE.md". Not for finding contradictions or broken pointers (use /skill-audit first).
document
Draft a technical document from an intent or a source. Triggers on "write the runbook / ADR / RCA / PR description / commit message / changelog / diagram / README / migration guide / API reference / experiment report / incident summary / onboarding doc / design doc". Markdown-first: produces a draft in a local file and NEVER publishes (no Confluence / Jira / Slack / GitHub posting — that is a separate concern). Reader-first voice: leads with the reader's question, cites every non-trivial claim to a repo path or quoted source, caps external quotes at 15 words, cuts filler. Audience-tuned (engineer / pm / exec / mixed) — the voice does not mix. GitHub context (PR / issue) is read via the gh CLI.