CtrlK
BlogDocsLog inGet started
Tessl Logo

finishing-a-development-branch

Verify tests pass, then present the integration options for a finished branch — merge locally, push and open a pull request, or keep it as-is — execute the choice, and clean up the worktree safely. This is the internal integration stage of the delivery-flow workflow. Use it only after implementation is verified and only when the user has authorized an integration decision, for example by saying "finish this branch", "merge my work", or "open a PR" — never activate it directly for an unrelated standalone request.

76

Quality

94%

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

The canonical home for this skill is tessleng/sdlc-assurance

SKILL.md
Quality
Evals
Security

Quality

Content

96%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 operational content: executable commands, verbatim menus, and validation gates on every destructive path, with a rationalization table that preemptively counters known failure modes. The only structural note is that everything lives in one file, which is acceptable at this size but leaves no headroom if the skill grows.

Suggestions

If the skill grows, move the Common Rationalizations table into references/rationalizations.md and keep a one-line pointer in SKILL.md, preserving the lean core workflow inline.

Consider adding the concrete forge-CLI example (e.g. `gh pr create --base <base-branch>`) as an inline hint for the common GitHub case, keeping the generic forge guidance as fallback.

DimensionReasoningScore

Conciseness

Purely operational content — exact menu blocks, bash snippets, and two lookup tables ("Quick Reference", "Common Rationalizations") — with no explanation of git concepts Claude already knows; every section adds non-obvious, workflow-specific constraints. The Common Rationalizations table targets LLM failure modes rather than padding, so it earns its tokens.

5 / 5

Actionability

Copy-paste-ready commands throughout ("GIT_DIR=$(cd "$(git rev-parse --git-dir)" 2>/dev/null && pwd -P)", "git worktree remove \"$WORKTREE_PATH\"") plus verbatim user-facing menu text. The one flexible step (PR creation "with the forge's tooling — its CLI if one is available, or the creation URL most forges print") is explicitly justified flexibility, not pseudocode.

5 / 5

Workflow Clarity

Steps 1–6 are clearly sequenced with explicit validation checkpoints on every risky path: tests must be green before the menu, merged-result tests must pass before cleanup ("nothing has been pushed, so the merge is local and recoverable"), discard requires a typed "discard" confirmation, and worktree-removal refusal triggers a file-status triage menu. Feedback loops are present for all destructive operations, matching the anchor-5 example.

5 / 5

Progressive Disclosure

Well-organized single-file structure with clear section headers and a Quick Reference table, but all content is inline with no reference split — the 220-line body exceeds the under-50-line simple-skill exception, and sections like "Common Rationalizations" could live in a references/ file. Not 5 because the anchor expects well-signaled one-level-deep references or an appropriately small single file; not 3 because what is inline is cohesively organized and navigable.

4 / 5

Total

19

/

20

Passed

Description

92%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: third-person, concrete, comprehensive, with explicit trigger phrases and clear scope boundaries including a negative constraint to prevent mis-triggering. The only gap is a few missing natural synonyms for the trigger terms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Verify tests pass", "merge locally, push and open a pull request, or keep it as-is", "execute the choice, and clean up the worktree safely" — with comprehensive coverage of the skill's behavior. Not 4 because there are no gaps in coverage of the actions it performs.

5 / 5

Completeness

Explicitly answers both questions: the what ("Verify tests pass, then present the integration options... execute the choice, and clean up the worktree safely") and the when ("Use it only after implementation is verified and only when the user has authorized an integration decision, for example by saying 'finish this branch'..."). Matches the anchor-5 example structure exactly.

5 / 5

Trigger Term Quality

Includes natural phrases users would actually say — "finish this branch", "merge my work", "open a PR" — which go beyond domain jargon. Not 5 because common synonyms like "land my changes", "integrate", or "ship it" are absent; not 3 because concrete natural trigger phrasings are explicitly quoted.

4 / 5

Distinctiveness Conflict Risk

Clear niche ("internal integration stage of the delivery-flow workflow") with explicit negative scoping — "never activate it directly for an unrelated standalone request" — minimizing overlap with generic branch-management or PR skills.

5 / 5

Total

19

/

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
tesslio/tessl-eval-demo
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.