CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-design-lineage

Persist design documents with branch tracking, revision chains, and cross-session discovery

52

Quality

58%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skill-design-lineage/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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.

The skill is strongly actionable — concrete, executable bash for every step — but undermined by sequencing incoherence (discovery after save, supersedes resolved after write), repetition of setup boilerplate, and a dangling cross-bundle reference. No validation checkpoints guard the write and chain-linking operations.

Suggestions

Fix the workflow order: move prior-design discovery and SUPERSEDES resolution (currently Steps 2-3) before the write in Step 1, so the heredoc's ${SUPERSEDES:+...} line actually populates the field, and add a post-write validation check (e.g., verify the file exists and the supersedes target resolves).

De-duplicate the SLUG/DESIGNS_DIR/BRANCH resolution block (define once, reference thereafter), state the immutability rule once, and drop the duplicated filename-format explanation — this would tighten conciseness without losing clarity.

Resolve the dangling `skills/blocks/domain-modeling.md` reference (either ship the file in references/ or remove the mention), and consider moving the document template and integration-notes sections into a reference file to reduce SKILL.md length.

DimensionReasoningScore

Conciseness

There is no padding explaining concepts Claude already knows, but the body is noticeably repetitive: the SLUG/DESIGNS_DIR/BRANCH resolution block is repeated nearly verbatim in Steps 1-4, the filename format is specified twice (Filename Format section and Step 1), and the immutability rule is stated three times (Overview, Step 1 note, Integration Notes). This fits 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than anchor 4, whose over-explanation is only minor.

3 / 5

Actionability

Guidance is largely copy-paste executable — complete bash blocks, a full heredoc template, a concrete filename example, and a revision-chain walk loop — matching 'mostly executable guidance with minor gaps'. It misses anchor 5 because Step 1's heredoc consumes ${SUPERSEDES} before any step establishes it, so the supersedes field is not actually populated by the shown flow.

4 / 5

Workflow Clarity

The four steps are clearly labeled with concrete commands, but the sequence is internally inconsistent: Step 2 says "Before writing a new design, search for related prior designs" yet is placed after the Step 1 write, and the supersedes linkage is computed in Step 3 only after the document has already been written in Step 1. There are also no validation checkpoints (e.g., verifying the file was written or the chain resolves). This matches 'steps listed but validation gaps; sequence present but checkpoints missing or implicit'.

3 / 5

Progressive Disclosure

The body is well-sectioned with headers, but it is a ~285-line single-file monolith in which the document template, cap enforcement, and integration cross-references could live in separate reference files, and the one external path it does cite — `skills/blocks/domain-modeling.md` — does not exist in the bundle (no references/, scripts/, or assets/ directories are present), making it a dangling, poorly signaled reference. This fits 'some structure but could be better organized' better than anchor 4.

3 / 5

Total

13

/

20

Passed

Description

58%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.

The description states a clear, moderately specific capability set but omits any usage trigger guidance, which both caps completeness and weakens trigger-term quality. Natural user-facing phrases (e.g., "save this design", "design history") are largely replaced by mechanism-level jargon.

Suggestions

Append an explicit trigger clause such as "Use when the user says 'save this design', 'create a design doc', or 'show design history'" — this would lift both completeness and trigger_term_quality.

Replace implementation jargon ("branch tracking", "revision chains", "cross-session discovery") with or supplement them by natural terms users say: "design docs", "specs", "prior designs", "design history".

Name one or two concrete operational actions (e.g., "saves design docs with revision chains and finds prior designs") to move specificity from several-actions toward comprehensive coverage.

DimensionReasoningScore

Specificity

The description lists several specific capabilities — "Persist design documents", "branch tracking", "revision chains", and "cross-session discovery" — matching the 'several specific actions; minor gaps' anchor. It falls short of anchor 5 because concrete operational actions (saving, searching, superseding revisions) and any artifact formats are not named, and is clearly above anchor 3 which expects only 1-2 concrete actions.

4 / 5

Completeness

It has a clear 'what' ("Persist design documents with branch tracking, revision chains, and cross-session discovery") but no 'when' — there is no "Use when..." clause or equivalent trigger guidance in the description. Per the judging guidelines this caps completeness at 3, matching the 'clear what but when is missing' anchor.

3 / 5

Trigger Term Quality

"design documents" is a natural term, but "branch tracking", "revision chains", and "cross-session discovery" are implementation jargon rather than phrases a user would naturally say, and common natural variations ("save this design", "design doc", "spec") are absent. This matches the 'some relevant keywords but missing common variations' anchor; it is above anchor 2 (which expects only generic keywords) but below anchor 4 (which expects good coverage with few gaps).

3 / 5

Distinctiveness Conflict Risk

Design-document lineage with revision chains is a fairly distinct niche with limited overlap risk against generic documentation or README skills. It matches 'mostly distinct; minor overlap risk' rather than anchor 5, because "design documents" alone could be confused with general documentation-creation skills absent more distinctive triggers.

4 / 5

Total

14

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
nyldn/claude-octopus
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.