CtrlK
BlogDocsLog inGet started
Tessl Logo

manage-local-skills

Analyze, standardize, validate, and sync locally maintained skills into agent skill directories with a `skills` CLI-aligned workflow. Use this skill when Codex needs to turn ad-hoc prompt or rules folders into reusable `SKILL.md`-based skills, install or sync one or more local skills from `./skills` into Claude, Cursor, CodeBuddy, Codex, or similar agent directories, or manage local skill path mappings and symlink or copy installation behavior.

75

Quality

93%

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

93%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, lean, and highly actionable content with a clear routing table and executable commands backed by real bundle files. The main gap is that validation is framed conditionally in the workflow rather than as an explicit checkpoint with a fix-retry loop, which matters given the batch/destructive install operations this skill performs.

Suggestions

Promote validation to an explicit numbered workflow step (e.g. 'Validate: run scripts/validate-skill.mjs; if it fails, fix and re-validate before proceeding') instead of the conditional 'when in doubt' phrasing, since installations and symlink/copy operations are batch/destructive.

Add a brief fix-and-retry feedback loop after the validation step so error recovery is explicit rather than implied by the self-check.

Clarify in the Workflow when the batch-confirmation rule from Operating rules applies (e.g. note in step 4 or 5 that multi-skill/multi-agent syncs require a summarized plan and user confirmation before execution).

DimensionReasoningScore

Conciseness

Lean and efficient with no padding or explanation of concepts Claude already knows; sections like Operating rules and Quick commands are tight directives where every token earns its place.

5 / 5

Actionability

Provides copy-paste ready executable commands with real arguments in Quick commands, a Routing table mapping each task to specific reference files and scripts, and concrete file/script pointers in the Workflow.

5 / 5

Workflow Clarity

A clear 6-step sequence is present with validation referenced (validate-skill.mjs 'before and after installation'), a Minimum self-check checklist, and confirmation gates, but validation is conditional ('when structure or path correctness is in doubt') rather than an explicit mandatory checkpoint with a fix-and-retry feedback loop embedded in the steps.

4 / 5

Progressive Disclosure

Clear overview in SKILL.md with well-signaled one-level-deep references; the Routing table maps each task to specific references/ and scripts/ files, all of which exist as real bundle files, and detail is appropriately split out of the overview.

5 / 5

Total

19

/

20

Passed

Description

92%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, specific description that clearly states capabilities and explicit use-when triggers with concrete agent targets and operation synonyms. Minor room to soften the technical 'when Codex needs to' framing into more natural user phrasing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Analyze, standardize, validate, and sync', 'install or sync', 'manage local skill path mappings and symlink or copy installation behavior' — with comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (analyze/standardize/validate/sync skills into agent directories) and 'when' ('Use this skill when Codex needs to turn ad-hoc prompt or rules folders into reusable SKILL.md-based skills, install or sync... or manage local skill path mappings').

5 / 5

Trigger Term Quality

Strong natural keyword coverage including synonyms ('install or sync', 'symlink or copy') and concrete agent names (Claude, Cursor, CodeBuddy, Codex), though the phrasing 'when Codex needs to' is slightly technical rather than user-voiced.

4 / 5

Distinctiveness Conflict Risk

Clear niche — locally maintained skills with a 'skills CLI-aligned workflow' and specific agent directories — with distinct triggers and minimal overlap with remote-registry or generic documentation skills.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
TencentCloudBase/CloudBase-AI-Toolkit
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.