Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

A5c AI/Knowledge Curation — measured AI agent skill | DecimalAI

a5c-ai/knowledge-curation

SkillScore68Maintained

Context priming before work (bd prime) and self-reflection after completion to extract patterns, gotchas, and decisions into the knowledge base.

by a5c-ai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Knowledge Management pack

decimalai skills pull a5c-ai-knowledge-curation

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/a5c-ai-knowledge-curation/SKILL.md

Raw file: /s/a5c-ai-knowledge-curation/SKILL.md ↗ · machine-readable summary at /s/a5c-ai-knowledge-curation.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 9d ago

Yes — +64% lift-37% tokens0% turns68% of whole cases pass with skill (15/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	8%	0%
case-04	✗→✓	▲ Improved	-56%	0%
case-05	✗→✓	▲ Improved	-60%	0%
case-06	✗→✓	▲ Improved	-40%	0%
case-07	✗→✓	▲ Improved	-69%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/31/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

a5c-ai / babysitter

library/methodologies/metaswarm/skills/knowledge-curation/SKILL.md

View on GitHub ↗

License MITImported 7/31/2026Version v1

Skill contents

SKILL.md

After completing work, BEFORE PR creation (reflect mode)
When recovering from context loss (recovery priming)

Knowledge Categories

| Category | File | Content | |----------|------|---------| | Critical Rules | facts.jsonl | MUST FOLLOW constraints | | Gotchas | gotchas.jsonl | Common pitfalls | | Patterns | patterns.jsonl | Codebase best practices | | Decisions | decisions.jsonl | Architectural choices with rationale | | Anti-Patterns | anti-patterns.jsonl | What NOT to do | | Codebase Facts | codebase-facts.jsonl | Structural information | | API Behaviors | api-behaviors.jsonl | Undocumented quirks |

Process

Prime Mode

Load knowledge base files for work type
Surface MUST FOLLOW rules first
Present GOTCHAS and PATTERNS
Load relevant DECISIONS

Reflect Mode

Extract patterns from completed work
Identify gotchas from review failures
Record architectural decisions with rationale
Persist to .beads/knowledge/

Tool Use

Invoke via babysitter process: methodologies/metaswarm/metaswarm-knowledge-cycle

Want to see if a5c-ai/knowledge-curation would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.