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.

67

Quality

81%

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

The canonical home for this skill is memory in Chachamaru127/claude-code-harness

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The body is a well-structured, token-efficient index that routes to real reference files with clean navigation. Its weakness is operational depth: the in-body workflow lacks validation checkpoints and concrete procedures, deferring most action to the references.

Suggestions

Add validation/verification checkpoints to the 実行手順 workflow for batch or destructive operations (plans merging, SSOT promotion, migration), e.g. a verify step after promoting decisions to SSOT.

Tighten the routing steps from abstract ('classify the request, read the file, execute') into specific decision criteria that map user intents directly to each reference file.

De-duplicate the sync-ssot-from-memory.md link, which appears in the feature table and again twice in the SSOT昇格 section.

DimensionReasoningScore

Conciseness

The body is lean: a compact feature table, terse MCP tool name lists ("harness_mem_search", "harness_mem_record_checkpoint"), and a 3-step procedure with no generic concept padding, fitting the level-3 "every token earns its place" anchor; the only minor redundancy is sync-ssot-from-memory.md being linked three times, which is not enough to drop to level 2.

3 / 3

Actionability

It names concrete tools and real file paths ("harness_mem_search", "references/plans-merging.md") but the body itself is a router that defers real procedures to reference files, and the steps "ユーザーのリクエストを分類 / 適切な参照ファイルを読む / その内容に従って実行" are abstract, matching the level-2 "some concrete guidance but incomplete" anchor rather than copy-paste-ready level-3.

2 / 3

Workflow Clarity

The 実行手順 section lists a 3-step sequence but has no validation or verification checkpoints, and the underlying operations (plans merging, SSOT promotion, migration) are batch/destructive enough that the rubric's note caps workflow clarity at 2 when feedback loops are missing; it is above level 1 because a clear sequence does exist.

2 / 3

Progressive Disclosure

The body is a clear overview that signals one-level-deep references via a feature table linking five real, existing reference files (e.g. "See [references/ssot-initialization.md](${CLAUDE_SKILL_DIR}/references/ssot-initialization.md)"), with content appropriately split and easy to navigate, matching the level-3 anchor.

3 / 3

Total

10

/

12

Passed

Description

90%

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 description: it states the skill's purpose, packs in natural trigger terms, and adds a clear negative-trigger exclusion to reduce misfires. The only soft spot is specificity, where actions are named generically ("Manage", "Guardian") rather than enumerated concretely.

DimensionReasoningScore

Specificity

Quotes "Manage SSOT, memory, and cross-tool memory search" and "Guardian of decisions.md and patterns.md" name the domain and a few actions (manage, search, guard), but do not enumerate multiple concrete actions the way a level-3 example like "extract text, fill forms, merge documents" would; it is more comprehensive than the level-1 "Helps with documents" vague anchor.

2 / 3

Completeness

It explicitly answers both what ("Manage SSOT, memory, and cross-tool memory search") and when ("Use when user mentions... or record this" plus a negative "Do NOT load for..." clause), matching the level-3 anchor that requires explicit triggers for both what and when.

3 / 3

Trigger Term Quality

Quotes "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" give broad, natural coverage of terms a user would actually say, matching the level-3 anchor for good keyword coverage.

3 / 3

Distinctiveness Conflict Risk

Quotes "Guardian of decisions.md and patterns.md" and "Do NOT load for: implementation work, reviews, ad-hoc notes, or in-session logging" carve a clear niche (SSOT/decisions.md/patterns.md stewardship) with a distinct negative-trigger clause that lowers conflict risk, fitting the level-3 anchor despite the broad term "memory".

3 / 3

Total

11

/

12

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.