CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

export

Create a review-safe PsychSift codebase archive with a manifest while excluding secrets, dependencies, build output, caches, logs, and machine-local state. Use when the user asks to package or export the repository for review.

Quality

88%

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

78%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.

An exceptionally lean, well-sequenced instruction-only body with an explicit verification step and appropriate guardrails. Its main weakness is actionability: the steps describe what to do without any executable commands or error-recovery guidance for the verification stage.

Suggestions

Add the concrete commands for each step — e.g., inspection via 'git ls-files && git status --ignored', archive creation via tar/zip with an explicit exclude list, and verification via 'unzip -l' / 'du -sh' — so guidance is executable rather than descriptive.

Add a feedback loop after step 5: what to do when the archive fails to open, the file list contains an excluded category (e.g., .env*), or the size is unexpectedly large (rebuild the archive with corrected excludes).

Specify the required contents and format of EXPORT_MANIFEST.md (e.g., file list, sizes, exclusion summary) so step 2 is reproducible.

DimensionReasoningScore

Conciseness

The body is six terse numbered directives with zero padding and no explanation of concepts Claude already knows (e.g., 'Inspect tracked, untracked, ignored, sensitive, generated, and oversized paths without printing secrets'). Every token earns its place, matching the level-5 anchor; level 4 would require some trimmable over-explanation, which is absent.

5 / 5

Actionability

Guidance names concrete artifacts ('EXPORT_MANIFEST.md', '.env*') and categories, but no executable commands are given for inspecting paths (e.g., git ls-files/status), creating the archive (tar/zip), or verifying it (unzip -l, du -sh) — matching the level-3 anchor of concrete-but-incomplete guidance with missing key details. It is not level 4 because that anchor expects concrete code or commands with only minor gaps, and none are present.

3 / 5

Workflow Clarity

The six steps form a clear sequence with an explicit validation checkpoint ('Verify the archive opens, inspect its file list, and confirm its size before handoff'), matching level 4 ('most checkpoints present'). It is not level 5 because there is no error-recovery feedback loop — what to do if the archive fails to open or the file list reveals a secret — and not capped at 3 since validation for this batch/packaging operation is present.

4 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, and needs no external references; the body is well-organized with a clear single heading and ordered steps, and no bundle files exist to mis-navigate. Per the rubric's simple-skill guideline this earns a 5; level 4 would imply organization gaps that are not present.

5 / 5

Total

17

/

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 description: third-person, concrete, and comprehensive on both capabilities and exclusions, with an explicit 'Use when...' trigger clause. The only gap is modest trigger synonym coverage (e.g., 'zip', 'archive', 'share').

DimensionReasoningScore

Specificity

Phrases like 'Create a review-safe PsychSift codebase archive with a manifest' and 'excluding secrets, dependencies, build output, caches, logs, and machine-local state' enumerate multiple concrete actions and a comprehensive exclusion list. It clearly matches the level-5 anchor (multiple specific concrete actions, comprehensive coverage) rather than level 4, which implies minor gaps in coverage.

5 / 5

Completeness

The description explicitly answers 'what' ('Create a review-safe... archive with a manifest while excluding...') and 'when' with a concrete 'Use when...' trigger clause ('package or export the repository for review'). This squarely matches the level-5 anchor with concrete trigger phrases; level 4 would require the 'when' to be less explicit or specific.

5 / 5

Trigger Term Quality

'Use when the user asks to package or export the repository for review' supplies good natural triggers ('package', 'export', 'repository', 'review'), matching the level-4 anchor of good coverage with a few natural terms missing. It is not level 5 because common variations users would naturally say — 'archive', 'zip', 'share', 'send the codebase' — are absent, though 'archive' does appear in the capability half.

4 / 5

Distinctiveness Conflict Risk

The skill is anchored to a specific project ('PsychSift codebase') and a specific task (exporting for review) with distinct triggers, giving it a clear niche with minimal conflict risk — the level-5 anchor. It is not level 4 because it does not merely overlap with closely related skills; the project-specific scope and secrets-exclusion framing make mis-triggering unlikely.

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

BigSimmo/PsychSift

Path

.agents/skills/export/SKILL.md

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.