CtrlK
BlogDocsLog inGet started
Tessl Logo

t3-code-continue-thread

Continue work from an earlier T3 Code thread by resolving its UUID, identifying the correct checkout or worktree, and producing a handoff for the normal agent.

63

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 ./skills/t3-code-continue-thread/SKILL.md
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.

A tight, actionable skill body: a runnable script invocation, concrete fields to inspect, sensible safeguards against silently switching checkouts, and explicit completion criteria. The only notable gaps are a repeated worktree-location instruction in step 1 and a missing recovery path when the UUID cannot be resolved.

DimensionReasoningScore

Conciseness

The body is lean with no padding and no explanation of concepts Claude already knows, but step 1's worktree-location guidance repeats the branch/commit lookup twice ("locate or create the checkout for the recorded branch/commit" then "use the recorded branch and commit to locate an existing git worktree"), so it fits anchor 4 with minor trimming possible.

4 / 5

Actionability

The guidance is mostly executable: a concrete command (`python3 <skill-dir>/scripts/find_thread.py <uuid> --full` pointing at a real bundled script) plus specific output fields to act on (`recommended_worktree.matches_recorded`, `matching_worktrees`, `found: false`); the handoff format itself is delegated to the external `handoff` skill, a minor gap.

4 / 5

Workflow Clarity

A clear numbered sequence (resolve, delegate, report) with explicit validation checkpoints (compare `matches_recorded`, the closing readiness criteria) and a partial error-recovery path (`matching_worktrees` fallback), but no recovery guidance when the UUID fails to resolve ("non-zero exit or `found: false`" states the failure without a next step), so it does not reach anchor 5.

4 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, organized into a clean numbered sequence, and its one reference — `scripts/find_thread.py` — is a real bundled file correctly signaled in place; no external references are needed, meeting the simple-skill exception for a top score.

5 / 5

Total

17

/

20

Passed

Description

70%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 specific, distinctive description with concrete named actions, but it omits an explicit "Use when..." trigger clause, leaving the invocation conditions implied rather than stated. Adding a trigger phrase with common synonyms (resume, hand off, new thread) would lift both completeness and trigger coverage.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to continue, resume, or pick up work from a previous T3 Code thread in a new thread."

Include natural synonyms users would say ("resume work", "hand off", "fresh thread") alongside "T3 Code thread" and "UUID" to improve trigger coverage.

Briefly state the output context of the handoff (for consumption by a fresh agent session) so the "what" is fully self-contained.

DimensionReasoningScore

Specificity

"resolving its UUID", "identifying the correct checkout or worktree", and "producing a handoff" name the domain and several concrete actions, but coverage is compact rather than comprehensive (e.g., what the handoff contains or where it goes is unstated), fitting anchor 4 more than 5.

4 / 5

Completeness

The "what" is clear (resolve UUID, identify checkout/worktree, produce handoff), but there is no explicit "Use when..." clause or equivalent trigger guidance; the "when" is only weakly implied by "Continue work from an earlier T3 Code thread", which caps completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Domain terms like "T3 Code thread", "UUID", "checkout", and "worktree" are natural for this niche, but common user phrasings such as "resume", "hand off", or "new/fresh thread" are missing, matching anchor 4 (good coverage, a few natural terms missing).

4 / 5

Distinctiveness Conflict Risk

"T3 Code thread" and its UUID define a clear niche with distinct triggers and minimal overlap with other skills, matching the anchor-5 example's profile of a specialized, hard-to-confuse skill.

5 / 5

Total

16

/

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
onmax/nuxt-skills
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.