CtrlK
BlogDocsLog inGet started
Tessl Logo

finish-feature

Finish a feature — run verification, an adversarial review gate (re-grounded on the original design doc + ticket ACs, not the plan) and a deferral-closure gate, then create the PR, retain learnings, and hand off cleanup to the terminal.

60

Quality

68%

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 ./devflow-plugin/skills/finish-feature/SKILL.md

The canonical home for this skill is finish-feature in AndreJorgeLopes/devflow

SKILL.md
Quality
Evals
Security

Quality

Content

73%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 well-sequenced, highly actionable completion pipeline with strong validation checkpoints and feedback loops. It is somewhat verbose in its rationale and reinforcement, and a few operational steps (subagent dispatch, ticket fetch) are described rather than given as concrete commands.

Suggestions

Collapse the trailing "Important" section into the steps it duplicates, or trim it to only the items not already enforced inline, to cut repeated tokens.

Tighten Step 4's "Why this step exists" rationale to one or two sentences; the detail is useful but currently overlong.

Make the parallel subagent dispatch and the Jira/Atlassian MCP ticket fetch concrete (e.g. example tool calls or exact subagent prompt templates) rather than prose descriptions.

DimensionReasoningScore

Conciseness

The body is mostly efficient with no basic-concept padding, but the "Important" section restates points already made in the steps and Step 4's "Why this step exists" rationale plus repeated emphases ("never self-attest", "lossy compression") could be tightened.

3 / 5

Actionability

Provides many copy-paste-ready commands (git, `devflow check`, `make flows-check`, the commit-message regex, PR section headings), but the parallel subagent dispatch and the Jira/Atlassian MCP ticket fetch are described rather than shown as concrete commands.

4 / 5

Workflow Clarity

A clear 9-step sequence with explicit validation checkpoints and feedback loops — the protected-branch hard stop, the checks-fail stop, the fail-loud empty-diff check, the severity-gated review, and commit-message approval before committing.

5 / 5

Progressive Disclosure

No bundle files exist, so scoring rests on structure; the skill is a single well-sectioned file (Preamble, Determinism, Steps 1–9, Important) with clearly signaled, one-level-deep external references (the determinism lib, Hindsight, the Jira MCP, /devflow:review).

4 / 5

Total

16

/

20

Passed

Description

63%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 is specific and distinctive, naming a comprehensive set of concrete actions for finishing a feature. Its main weakness is the absence of an explicit "Use when…" trigger clause and a reliance on pipeline jargon over natural user keywords.

Suggestions

Add an explicit trigger clause, e.g. "Use when a feature is implementation-complete and ready to be verified, reviewed, and turned into a PR."

Soften internal jargon ("deferral-closure gate", "re-grounded on ticket ACs") or pair it with natural phrasing so users who say "wrap up my feature" or "open a PR for this work" match the skill.

Lead with the user-facing outcome before the mechanism, e.g. "Finish a feature: verify it, review it against the original design, then open the PR."

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "run verification", "an adversarial review gate", "a deferral-closure gate", "create the PR", "retain learnings", and "hand off cleanup" — giving comprehensive coverage of the feature-finishing pipeline.

5 / 5

Completeness

The "what" is clear and detailed, but there is no explicit "Use when…" clause; the "when" is only weakly implied by the leading "Finish a feature —", which caps completeness at 3 per the guideline.

3 / 5

Trigger Term Quality

"Finish a feature" and "create the PR" are natural phrases a user would say, but much of the rest is internal jargon ("deferral-closure gate", "ticket ACs", "re-grounded") with few synonyms or common variations.

3 / 5

Distinctiveness Conflict Risk

It carves a distinct niche (a full feature-completion pipeline with review and deferral gates), with only minor overlap risk against generic PR-creation or code-review skills.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
AndreJorgeLopes/devflow
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.