CtrlK
BlogDocsLog inGet started
Tessl Logo

memory

Manage SSOT, memory, and cross-tool memory search. Guardian of decisions.md and patterns.md. Use when user mentions memory, SSOT, decisions.md, patterns.md, merging, migration, SSOT promotion, sync memory, save learnings, memory search, harness-mem, past decisions, or record this. Do NOT load for: implementation work, reviews, ad-hoc notes, or in-session logging.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

72%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.

Well-structured index skill with excellent progressive disclosure and concrete tooling references. The main gap is workflow clarity: destructive/batch operations (migration, SSOT promotion, merging) lack explicit validation checkpoints in the body's workflow.

Suggestions

Add an explicit validation/checkpoint step to the 実行手順 workflow — e.g., confirm scope with the user and re-verify current state before any destructive migration or SSOT promotion, rather than only stating guardrail principles.

De-duplicate the sync-ssot-from-memory.md reference (it appears in both the 機能詳細 table and the SSOT昇格 section) to tighten conciseness.

Tighten or shorten the D22 explanatory paragraph to only what is needed to point to the decision record, keeping the body an index.

DimensionReasoningScore

Conciseness

The body is a lean index with purposeful guardrail principles, but the D22 paragraph is mildly explanatory and sync-ssot-from-memory.md is referenced twice, leaving minor redundancy to trim.

4 / 5

Actionability

Provides concrete MCP tool names (harness_mem_search, harness_mem_record_checkpoint, etc.) and an executable command (/memory ssot), but detailed per-task steps are deferred to reference files, leaving minor gaps.

4 / 5

Workflow Clarity

A 3-step sequence is present (classify request, read reference file, execute), but validation checkpoints are absent; because migration/promotion/merging are destructive or batch operations, the rubric caps workflow clarity at 3.

3 / 5

Progressive Disclosure

Clear overview table points to five one-level-deep reference files, all verified to exist, with easy navigation — a textbook match for the anchor 5 example.

5 / 5

Total

16

/

20

Passed

Description

95%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 strong, third-person description that clearly states capability, provides exhaustive natural trigger terms, and actively reduces conflict risk with negative triggers. The only minor weakness is slightly generic action verbs.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('Manage SSOT, memory, and cross-tool memory search', 'Guardian of decisions.md and patterns.md'); verbs are slightly generic so it sits just below the comprehensive anchor 5.

4 / 5

Completeness

Explicitly answers both 'what' (Manage SSOT/memory/cross-tool search) and 'when' ('Use when user mentions memory, SSOT, ...') with concrete trigger phrases, plus negative triggers.

5 / 5

Trigger Term Quality

Comprehensive natural keyword coverage with synonyms ('save learnings', 'past decisions', 'record this', 'memory search') and file/tool references ('decisions.md', 'patterns.md', 'harness-mem'), matching the anchor 5 example.

5 / 5

Distinctiveness Conflict Risk

Distinct niche triggers (harness-mem, SSOT promotion, decisions.md/patterns.md) combined with an explicit 'Do NOT load for: implementation work, reviews, ad-hoc notes' clause minimize conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 7 missing, 7 deeper-than-1-level, 1 suspicious

Warning

Total

15

/

16

Passed

Repository
Chachamaru127/claude-code-harness
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.