CtrlK
BlogDocsLog inGet started
Tessl Logo

uctm-init

Initialize uc-taskmanager for the current project. Creates works/ directory and configures Bash permissions in .claude/settings.local.json. Use when the user says "uctm init", "initialize uctm", "uctm 초기화", or "초기화".

64

Quality

75%

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 ./plugins/agents-uc-taskmanager/skills/init/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 body is efficient and actionable with a clear sequence and good single-file organization. Its main weakness is workflow clarity: the batch permission merge writes to settings.local.json without a verification step confirming the result is still valid.

Suggestions

Add a post-merge verification step, e.g. re-read .claude/settings.local.json and confirm it parses as valid JSON with the expected total permission count before reporting success.

Make the step instructions more literally executable (e.g. 'mkdir -p works' and a concrete merge snippet) to lift actionability from pseudocode to copy-paste-ready.

Consider whether the duplicated Read/Edit/Write glob variants (/**) and (**) are both needed; trimming redundant entries would tighten conciseness without losing capability.

DimensionReasoningScore

Conciseness

Lean body that assumes Claude's competence and avoids explaining known concepts; the long permission JSON is necessary data rather than padding, with only minor trim potential (duplicate Read/Edit/Write glob patterns).

4 / 5

Actionability

Gives a concrete target file path, an exact JSON array to merge, and explicit skip-duplicate behavior; not a 5 because the steps are pseudocode-style instructions rather than literal executable shell commands.

4 / 5

Workflow Clarity

A clear 3-step sequence with existence checks and a user-confirmation gate is present, but the batch permission-merge lacks a post-write validation that settings.local.json remains valid JSON, triggering the batch-operation cap of 3.

3 / 5

Progressive Disclosure

Single self-contained file with well-organized numbered sections and an Arguments block; not a 5 because the inlined permission array is bulk that sits at the edge of belonging in a reference, and the body exceeds the simple-skill line threshold.

4 / 5

Total

15

/

20

Passed

Description

82%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 description that clearly states what the skill does and when to use it, with concrete bilingual trigger phrases and a distinct niche. The only limitation is that it names just two concrete actions, capping specificity at the midpoint.

DimensionReasoningScore

Specificity

Names two concrete actions — 'Creates works/ directory' and 'configures Bash permissions in .claude/settings.local.json' — matching the 1-2 concrete-actions anchor; not a 4 because coverage is limited to those two actions rather than 'several.'

3 / 5

Completeness

Explicitly answers both 'what' (initialize, create works/, configure permissions) and 'when' with concrete trigger phrases via the 'Use when the user says...' clause, matching the score-5 anchor.

5 / 5

Trigger Term Quality

Provides good natural-phrase coverage — 'uctm init', 'initialize uctm', 'uctm 초기화', '초기화' — across two languages with synonyms; not a 5 because the set is narrow and lacks the breadth implied by the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The uctm-specific and Korean 초기화 triggers carve a clear niche that is unlikely to fire for unrelated skills, matching the minimal-conflict-risk anchor.

5 / 5

Total

17

/

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
davepoon/buildwithclaude
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.