CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

lore

Curating cross-agent knowledge and institutional memory: extracts patterns from agent journals into METAPATTERNS.md, detects knowledge decay, propagates best practices. Use for memory curation.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/lore/SKILL.md

The canonical home for this skill is lore in simota/agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, unusually concrete orchestration skill: clear sequenced workflow, numeric thresholds throughout, and excellent reference signaling via the Reference Map and per-phase Read columns. The main costs are token waste from a duplicated HTML header comment, repeated TTL/routing/boundary content, and citation padding, plus missing worked examples for its two most common outputs (a METAPATTERNS.md entry and a LORE_INSIGHT message).

Suggestions

Delete or collapse the ~30-line HTML CAPABILITIES_SUMMARY comment block — it restates the body (capabilities, collaboration patterns, partners) at full length and is pure token overhead on every load.

State the Domain TTL multiplier table once (in Knowledge Decay Detection) and reference it from the Core Contract, and consolidate the routing/boundary guidance repeated across Trigger Guidance, Output Routing, and Collaboration into one section.

Add one worked METAPATTERNS.md catalog entry and one sample LORE_INSIGHT message so the most common outputs have copy-adaptable templates in the body.

DimensionReasoningScore

Conciseness

The body is mostly dense, project-specific protocol Claude would not already know, but there is real, repeated waste: the ~30-line HTML CAPABILITIES_SUMMARY comment duplicates body content wholesale, the Domain TTL multiplier table appears twice (Core Contract and Knowledge Decay Detection), and routing/boundary guidance is repeated across Trigger Guidance, Output Routing, and Collaboration. Justification prose ("Ebbinghaus curve", "MIT Sloan", "PMC meta-analysis", "temporal knowledge graph research shows") adds tokens without operational value. This fits 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than 2, since the excess is duplication and citation padding rather than explaining concepts Claude already knows.

3 / 5

Actionability

Guidance is highly concrete and executable for an instruction-only skill: exact clustering thresholds (>=80% / 50-79% / <50%), numeric freshness scoring with alert thresholds (<85%, <70%), confidence bands by evidence count (1=Anecdote ... 11+=Foundational), TTL multipliers per domain, explicit ID and journal formats ([DOMAIN]-[TYPE]-[NNN], '## YYYY-MM-DD - [Discovery/Insight]'), and a state-to-action table. It is not a 5 because there is no worked example of a METAPATTERNS.md catalog entry or a LORE_INSIGHT/LORE_ALERT message — the most common outputs have no template or sample inline.

4 / 5

Workflow Clarity

The HARVEST → SYNTHESIZE → CATALOG → PROPAGATE → AUDIT workflow is clearly sequenced with per-phase required actions, key rules, and read references; destructive operations (archiving/removing patterns) are guarded by explicit validation gates (Ask First for <3 evidence, Never auto-archive FAILURE/ANTI by time alone, FOUNDATIONAL requires human decision) and the freshness table maps each state to a default action. It is not a 5 because error-recovery loops are thin — 'contradiction resolution workflow' is invoked by name with no inline steps, and audit findings route to a reference rather than a closed feedback loop.

4 / 5

Progressive Disclosure

Structure and signaling are strong: a Reference Map with 'Read this when' guidance, per-recipe 'Read First' columns, per-phase 'Read' pointers, and references that appear one level deep. It is not a 5 because the referenced files (reference/*.md, _common/*.md) are not present in the bundle, so the navigation layer cannot deliver, and substantial detail is inlined in SKILL.md that clearly belongs in those references (the full Architecture node/edge enumeration, the TTL multiplier table duplicated inline despite reference/decay-detection.md being declared authoritative).

4 / 5

Total

15

/

20

Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A solid description with a clear what/when split, third-person voice, concrete named actions, and a distinct niche. The main weakness is the terse, single-purpose trigger clause ("Use for memory curation") that undersells the breadth of capabilities described in the body.

Suggestions

Broaden the 'Use when...' clause to cover the described capabilities, e.g. "Use for memory curation, mining patterns from agent journals or postmortems, freshness/decay audits, or propagating best practices to consuming agents."

Add 1-2 missing capability actions (e.g., postmortem mining, contradiction detection) to close the specificity gap between the description and the body's actual scope.

DimensionReasoningScore

Specificity

The description names several concrete actions — "extracts patterns from agent journals into METAPATTERNS.md", "detects knowledge decay", "propagates best practices" — which matches the anchor for several specific actions with minor gaps. It is not a 5 because coverage is incomplete relative to the skill's actual capabilities (postmortem mining, contradiction detection, and pruning are absent), and not a 3 because it goes beyond 1-2 actions with a named artifact target.

4 / 5

Completeness

It clearly answers 'what' (curating cross-agent knowledge; extracting patterns into METAPATTERNS.md; detecting decay; propagating practices) and includes an explicit 'when' clause ("Use for memory curation"), matching the anchor where both are present but 'when' could be more specific. It is not a 5 because the trigger clause is narrow — it covers only memory curation and omits triggers for decay detection, journal pattern extraction, or propagation; not a 3 because an explicit 'Use for...' clause exists.

4 / 5

Trigger Term Quality

It carries good natural keywords a user in this ecosystem would say — "agent journals", "knowledge decay", "best practices", "memory curation" — matching the 'good keyword coverage; a few natural terms missing' anchor. It is not a 5 because common variations like "postmortems", "patterns", "freshness", or "institutional memory" (as a trigger phrase) are missing, and not a 3 because coverage goes beyond a couple of generic keywords.

4 / 5

Distinctiveness Conflict Risk

The niche is clear — cross-agent knowledge curation with a distinct artifact (METAPATTERNS.md) and distinct triggers — but "knowledge", "memory", and "best practices" are broad terms with minor overlap risk against general memory/notes skills, matching the 'mostly distinct; minor overlap risk' anchor. It is not a 5 because the shared vocabulary is generic enough that closely related skills could compete for some queries.

4 / 5

Total

16

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

simota/agent-skills

Path

.claude/skills/lore/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.