CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

unfreeze

Clear the freeze boundary set by /freeze, allowing edits to all directories again. Use when you want to widen edit scope without ending the session. Use when asked to "unfreeze", "unlock edits", "remove freeze", or "allow all edits".

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

Excellent single-purpose skill content: fully executable commands with error-tolerant fallbacks, a clear state check that reports the prior boundary, and tight follow-up guidance about hook behavior and re-freezing. Nothing is padded and nothing is missing for the task's scope.

DimensionReasoningScore

Conciseness

The body is lean with zero concept over-explanation: one summary sentence, two command blocks, and a short follow-up note ("Tell the user the result... To re-freeze, run /freeze again"). Every line is a command or direct instruction, matching anchor 5 ("Lean and efficient; every token earns its place").

5 / 5

Actionability

Both bash blocks are fully executable and copy-paste ready, with robust fallbacks ("${CLAUDE_PLUGIN_DATA:-$HOME/.gstack}", "2>/dev/null || true") and branches for both states (boundary set vs. "No freeze boundary was set"). This matches anchor 5 ("Fully executable; copy-paste ready").

5 / 5

Workflow Clarity

This is a simple, single-purpose skill and the single action is unambiguous: check the state file ("if [ -f \"$STATE_DIR/freeze-dir.txt\" ]"), remove it, report the prior boundary to the user. The existence check is an explicit checkpoint and the content closes the loop ("Note that /freeze hooks are still registered... To re-freeze, run /freeze again"), so the simple-skill exception applies; no destructive or batch operation requires further validation.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references, and the content is well organized (summary, telemetry block, one clearly headed section "## Clear the boundary", follow-up notes). Per the rubric guideline this earns a 5 with just well-organized sections.

5 / 5

Total

20

/

20

Passed

Description

90%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: concrete what, explicit trigger phrases with good synonym coverage, and clear pairing with the companion /freeze skill. The only deduction is the second-person phrasing ("Use when you want to widen edit scope") in the trigger clause.

Suggestions

Rewrite the trigger clause in third person, e.g. "Use when widening edit scope without ending the session is desired" or drop the 'you' clause since the quoted trigger phrases already cover the when.

Optionally add one or two more natural variants such as "disable the freeze" or "lift the freeze" to the trigger list.

DimensionReasoningScore

Specificity

"Clear the freeze boundary set by /freeze, allowing edits to all directories again" precisely names the single concrete action and its effect (base 4), but the rubric penalizes second-person voice — "Use when you want to widen edit scope without ending the session" — by reducing specificity by 1. It does not list several distinct actions, matching anchor 3 ("Names domain and 1-2 concrete actions") more than anchor 4 after the penalty.

3 / 5

Completeness

The what is explicit ("Clear the freeze boundary set by /freeze, allowing edits to all directories again") and the when is explicit with concrete trigger phrases ("Use when asked to 'unfreeze', 'unlock edits', 'remove freeze', or 'allow all edits'"). This matches the anchor 5 example structure exactly and is well above anchor 4, whose 'when' is only generically phrased.

5 / 5

Trigger Term Quality

"unfreeze", "unlock edits", "remove freeze", "allow all edits", and "widen edit scope" give comprehensive synonym coverage of the natural phrases a user would say for this single narrow concept, with no relevant file extensions to include. It clearly matches anchor 5 rather than anchor 4 ("a few natural terms missing") because the quoted trigger list covers all common phrasings.

5 / 5

Distinctiveness Conflict Risk

The description is anchored to a specific companion skill ("set by /freeze") and uses trigger terms unique to this operation, so it is clearly distinguishable and unlikely to fire for the wrong skill. No overlap with generic skills since freeze/unfreeze is a distinct niche.

5 / 5

Total

18

/

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

valeriibeck-star/claude-skills

Path

skills/gstack/.agents/skills/gstack-unfreeze/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.