fla-mr-readiness

Checklist and workflow for preparing an MR/PR in the FLA repo. Covers CONTRIBUTING.md compliance, test plan, benchmark evidence, and PR body structure.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/fla-mr-readiness/SKILL.md

Quality

Content

75%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 skill body is a concise, actionable pre-PR checklist with executable commands, a reusable PR-body template, and a clear sequenced workflow including a test-validation feedback loop. Structure is clean and well-sectioned with an appropriately signaled cross-reference to a sibling skill.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence — a short purpose line, a numbered checklist with concrete commands, and a compact PR-body template; only minor introductory phrasing could be trimmed, matching the 'efficient; minor instances of over-explanation' anchor.	4 / 5
Actionability	Provides concrete executable commands ("gh pr list --repo ...", "python scripts/find_dependent_tests.py <changed_file_or_dir>") plus a copy-paste PR-body template and a specific wrapper list; minor gaps (e.g. 'run those tests locally' is unspecified) keep it just below fully copy-paste ready.	4 / 5
Workflow Clarity	A clearly sequenced 7-step pre-flight checklist with an explicit validation/feedback loop in step 4 ("Run those tests locally and ensure they pass... if it still fails, explain why in the PR"); not a 5 because some checkpoints are implicit and there is no final pre-submit verification gate.	4 / 5
Progressive Disclosure	Content is organized into well-labeled sections (Pre-flight checklist, Suggested PR body structure, Important reminders) with a clearly signaled cross-reference to the fla-nvidia-performance skill; no bundle files exist to split further, and the inline template is appropriately placed, matching 'good structure; references mostly clear'.	4 / 5
	Total	16 / 20 Passed

Description

58%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 conveys what the skill covers but omits any explicit 'use when' trigger guidance, which caps completeness. Trigger-term coverage is relevant but thin on natural synonyms. It is well-scoped to the FLA repo, keeping conflict risk low.

Suggestions

Add an explicit trigger clause, e.g. 'Use when preparing to open a pull request or merge request in the flash-linear-attention (FLA) repo.'

Include natural synonyms users actually say — 'open a PR', 'merge request', 'code review', 'submit a change' — to improve trigger-term quality.

Consider stating the discrete actions as verbs (e.g. 'Verify CONTRIBUTING.md compliance, plan tests, gather benchmark evidence, draft the PR body') to push specificity toward 5.

Dimension	Reasoning	Score
Specificity	Names the domain (MR/PR prep in FLA repo) and lists several concrete coverage areas — "CONTRIBUTING.md compliance, test plan, benchmark evidence, and PR body structure" — which matches the 'lists several specific actions; minor gaps' anchor; not a 5 because the actions are areas rather than a comprehensive enumerated action set.	4 / 5
Completeness	Clearly states what the skill does ("Checklist and workflow for preparing an MR/PR") but provides no 'Use when...' trigger clause; per the judging guidelines a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant terms ("MR/PR", "pull request" implied, "CONTRIBUTING.md", "test plan", "benchmark") but lacks common natural variations/synonyms a user would say (e.g. "open a PR", "merge request", "code review"), fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Scoped to "the FLA repo" with MR/PR-specific triggers, making it mostly distinct with only minor overlap risk against neighboring repo/dev-process skills; not a 5 because general PR-prep guidance could overlap with similar skills.	4 / 5
	Total	14 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: fla-org/flash-linear-attention
Path: .agents/skills/fla-mr-readiness/SKILL.md
Commit: 27967b9

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.