CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

full-stop

Trigger this if the user says 'full stop', even as a closing "Full stop." that reads like emphasis.

Quality

72%

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 ./plugins/tstack/skills/full-stop/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 lean, well-structured delta skill that cleanly specifies what it overrides versus its parent skill, with strong validation checkpoints around pushes and the handoff gate. Its main weakness is total dependence on the external full-send SKILL.md, which is neither bundled nor summarized, so the skill is not executable from this bundle alone.

Suggestions

Inline a one-line definition of full-send's merge gate (the specific checks that must pass) so the readiness verdict is checkable without leaving this file.

Verify the '../full-send/SKILL.md' path resolves in the deployment environment, or inline minimal fallback steps for proof/review/babysitting so the skill degrades gracefully if the sibling is missing.

DimensionReasoningScore

Conciseness

Every line is instructive — 'Never merge it', 'Disable existing auto-merge and remove the PR from any merge queue before work begins', 'call `unwatch_pull_request` before the handoff' — with zero padding and no explanation of concepts Claude already knows. The 47-line body assumes competence throughout.

5 / 5

Actionability

Concrete, executable deltas are given (allowed git operations including `--force-with-lease`, 'Fetch the target branch and check the live PR's head, base, checks, reviews, and mergeability', the `unwatch_pull_request` call), but the core workflow is delegated entirely to '../full-send/SKILL.md', which is not part of this bundle, so the guidance is not self-contained. Not score 5 because executing the proof/review/babysitting steps requires an external file; not score 3 because the override rules and handoff criteria present here are specific and directly executable.

4 / 5

Workflow Clarity

The delta workflow is clearly sequenced with explicit checkpoints: 'check again before each push', 'recheck behavior changes and meaningful conflict fixes before handoff', 'Confirm it is open, not a draft', plus a three-outcome decision checklist (Ready / Waiting / Blocked). Not score 5 because the underlying sequence (proof rules, review, merge gate) is inherited from full-send rather than restated, leaving the full end-to-end order implicit across two files.

4 / 5

Progressive Disclosure

Under 50 lines with no bundle files of its own, well-organized into 'No merging' and 'Stop at the gate' sections, and a single clearly-signaled one-level-deep reference ('Read [full-send](../full-send/SKILL.md)'). The simple-skill exception applies; the only caveat is that the referenced sibling skill is not verifiable within this bundle.

5 / 5

Total

18

/

20

Passed

Description

46%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 nails the trigger — precise, natural, and even covering a tricky emphatic usage — but says nothing about what the skill actually does. A user (or Claude scanning skill descriptions) learns when to invoke it but not what work to expect, which is the anchor case of 'when' without 'what'.

Suggestions

Add a capability statement, e.g. 'Prepares a pull request through testing, proof, and review until it is merge-ready, but never merges it.'

Name the concrete actions in the description: run the test suite, request review, verify CI checks and mergeability, resolve conflicts, then hand off unmerged.

Combine what and when in one line: '...Never merges it. Use when the user says 'full stop' or closes a request with "Full stop." as emphasis.'

DimensionReasoningScore

Specificity

The description contains no action verbs or capability statements at all — the only concrete content is 'Trigger this if the user says 'full stop''. It names no domain and no actions, matching the 'no concrete actions' anchor; it cannot score 2 because even 'minimal or generic' actions are absent.

1 / 5

Completeness

Only the 'when' half is present (explicit trigger guidance on 'full stop'); the 'what' — preparing a PR to merge-ready state without merging — is entirely missing from the description. This matches the anchor 'only 'when' is present without 'what''; it cannot score 3 because there is no 'what' at all, only a weak implication from the skill name.

2 / 5

Trigger Term Quality

'full stop' is exactly the natural phrase a user would say, and the description even captures the disguised variant 'even as a closing "Full stop." that reads like emphasis'. Not score 5 because coverage is limited to that single phrase family — no synonyms or alternate phrasings are included; not score 3 because the covered trigger is precise and includes a non-obvious usage pattern.

4 / 5

Distinctiveness Conflict Risk

'full stop' is a distinctive trigger phrase with clear separation from the closely related 'full send' skill, and the deliberate capture of the emphatic closing usage is an explicit design choice rather than accidental overlap. Conflict risk with other skills is minimal.

5 / 5

Total

12

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

adamsardo/tstack-marketplace

Path

plugins/tstack/skills/full-stop/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.