CtrlK
BlogDocsLog inGet started
Tessl Logo

trellis-finish-work

Wrap up the current session: verify quality gate passed, remind user to commit, archive completed tasks, and record session progress to the developer journal. Use when done coding and ready to end the session.

72

Quality

87%

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

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.

The body is an exemplary short workflow skill: lean, fully executable, with a clearly sequenced process and explicit validation/routing checkpoints for a batch archive operation. No bundle files are needed and the structure is well organized, so it meets the top anchor on every dimension.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no padding about what git or Python is, and every line (commands, routing rules, the final git-log ordering) earns its place. It matches the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

Fully executable, copy-paste-ready bash commands are given for every step (get_context.py --mode record, git status --porcelain, task.py archive, add_session.py with --commit "hash1,hash2"), and the routing logic in Step 2 gives concrete decisions for each case.

5 / 5

Workflow Clarity

A clearly sequenced 4-step process with explicit validation checkpoints — Step 2 classifies dirty paths and bails out vs. continues vs. asks, with a feedback loop back to Phase 3.4; the batch archive operation has guardrails and a confirmation gate, satisfying the feedback-loop requirement.

5 / 5

Progressive Disclosure

This is a single-purpose skill under 50 lines with no external bundle files (references/, scripts/, assets/ absent) and well-organized section headers, qualifying for the simple-skill exception that lets progressive disclosure score 5 on organization alone.

5 / 5

Total

20

/

20

Passed

Description

75%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 clearly states both what the skill does (four concrete wrap-up actions) and when to use it (ending a coding session), with natural trigger language. It is strong and specific but stops just short of the fully comprehensive, synonym-rich top anchor.

Suggestions

Broaden trigger coverage with natural synonyms, e.g. 'Use when done coding, wrapping up a session, or ready to end work for the day'.

Tighten the 'what' with the specific artifacts touched, e.g. 'archive the active task and append an entry to the developer journal' to reduce overlap with generic wrap-up skills.

DimensionReasoningScore

Specificity

Lists four concrete actions ('verify quality gate passed, remind user to commit, archive completed tasks, and record session progress'), matching the anchor for several specific actions with minor coverage gaps; not quite the comprehensive multi-action list of a 5.

4 / 5

Completeness

Both 'what' (the four wrap-up actions) and explicit 'when' ('Use when done coding and ready to end the session') are present; the trigger could be slightly more specific, matching the 4 rather than the fully explicit 5.

4 / 5

Trigger Term Quality

'Use when done coding and ready to end the session' is a natural phrase users would say, but keyword coverage is good rather than comprehensive — missing synonyms/variations like 'session' or 'wrap up'.

4 / 5

Distinctiveness Conflict Risk

The session-wrap-up niche with 'end the session' triggers is mostly distinct with minimal overlap risk; it does not quite reach the minimal-conflict clarity of a 5 because 'wrap up' is a somewhat general verb.

4 / 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mindfold-ai/Trellis
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.