CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

source-command-push-all

Stage all changes, create commit, and push to remote (use with caution)

Quality

79%

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 ./.agents/skills/source-command-push-all/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 a highly actionable, well-sequenced workflow with strong validation checkpoints, a confirmation gate, and error-recovery feedback loops appropriate for a destructive batch operation. Its main weakness is token efficiency: it explains git and conventional-commit basics Claude already knows and duplicates the safety checks across two sections, and as a longer single-file skill it misses the simple-skill exception for progressive disclosure.

Suggestions

Cut explanations of things Claude already knows: drop the per-command glosses ("git status - Show modified/added/deleted/untracked files"), the conventional-commit type list, and the standard git failure remedies.

Merge the "When to Use" Good/Avoid lists into the Safety Checks section to remove the duplicated guidance.

Move the secret/API-key pattern catalog into a references/ file (e.g., secrets-checklist.md) linked from the Safety Checks section to reduce SKILL.md length.

DimensionReasoningScore

Conciseness

Concrete content dominates, but there is more than minor over-explanation: "git status - Show modified/added/deleted/untracked files" explains a command Claude knows, the full conventional-commit type list ("feat, fix, docs, style, refactor...") restates common knowledge, standard git error recovery ("Non-fast-forward: git pull --rebase && git push") is taught, and the "When to Use" Good/Avoid lists restate the Safety Checks section. This sits between the 3 and 4 anchors, closer to 3 given the accumulated redundancy.

3 / 5

Actionability

Guidance is copy-paste ready throughout: exact commands ("git add .", "git status", "git commit -m \"$(cat <<'EOF'...)", "git push"), specific secret filename patterns ("*.pem", "id_rsa", "*_API_KEY"), an explicit confirmation template, and a concrete commit-message example covering the common case; the only placeholder ([Generated commit message]) is by design with step 5 supplying the format and example, so it fits the 5 anchor rather than the 4 anchor's "minor gaps".

5 / 5

Workflow Clarity

Seven clearly sequenced steps with explicit validation for this destructive/batch operation: pre-flight safety checks with a STOP list, a hard confirmation gate ("WAIT for explicit 'yes' before proceeding"), post-add staging verification ("git status # Verify staging"), post-push verification ("git log -1 --oneline --decorate"), and feedback loops for error recovery in the Error Handling section — matching the 5 anchor's checklist plus validation plus recovery loops; the destructive-operation cap at 3 does not apply since validation is present.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent) and none are referenced, and the body is well-sectioned (Workflow, Error Handling, When to Use, Alternatives) for a self-contained single-command workflow; however, at ~155 lines it exceeds the under-50-line simple-skill exception, and inline content like the API-key pattern catalog could live in a reference file, so it fits the 4 anchor's "good structure, minor organization gaps" rather than a 5.

4 / 5

Total

17

/

20

Passed

Description

66%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, concrete, third-person "what" covering the full stage-commit-push flow, but omits any explicit "when to use" trigger clause, capping completeness. Adding a trigger clause with natural phrases (e.g., "Use when the user asks to push all changes or run push-all") would raise both completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks to commit and push all changes, run push-all, or publish everything to the remote."

Include natural synonym phrasing users would say ("git push", "push everything", "publish all changes") to broaden trigger-term coverage.

Consider naming the command context (push-all / migrated source command) in the description to sharpen distinctiveness against generic git commit skills.

DimensionReasoningScore

Specificity

"Stage all changes, create commit, and push to remote" lists three concrete actions that fully sequence the skill's behavior, matching the anchor for several specific actions; it stops short of the 5 anchor's comprehensive multi-action listing and is well above the 1-2 action anchor at 3.

4 / 5

Completeness

The "what" is clear (stage, commit, push) but there is no "Use when..." clause or equivalent trigger guidance — "(use with caution)" is a warning, not a usage trigger — which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Natural keywords users would say are present — "stage all changes", "commit", "push to remote" — giving good coverage of the git commit/push domain; synonyms like "git push", "publish", or "push everything" are missing, so it does not reach the comprehensive-synonym coverage of the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

"Stage all changes" plus the caution marker carves out a distinct bulk-push niche with only minor overlap risk against closely related git skills (e.g., commit-message or PR workflows); it is not generic enough to conflict broadly, but lacks distinctive trigger phrasing for a 5.

4 / 5

Total

15

/

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

tonykay/transcriber

Path

.agents/skills/source-command-push-all/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.