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

76%

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

82%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 content is highly actionable, with concrete commands and a complete PR template, and is well-structured with clearly signaled repo references. It is held back only by minor conciseness redundancy and the absence of an explicit pre-PR gating checkpoint.

Suggestions

Add a single explicit gate line such as 'Do not open the PR until every pre-flight item above passes or is marked N/A' to push workflow clarity toward 5.

Trim the 'Important reminders' benchmark bullets that duplicate the PR template's Benchmark / NCU section to reduce conciseness redundancy.

Consider referencing the PR template by path with only a short inline excerpt, leaving the canonical body to pull_request_template.md, to tighten progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no primer on what a PR is), with concrete commands and a copy-paste template; minor redundancy between the 'Important reminders' benchmark bullets and the PR template matches 'Efficient; minor instances of over-explanation that could be trimmed' rather than 5.	4 / 5
Actionability	Executable commands ('gh pr list --repo ...', 'python scripts/find_dependent_tests.py'), named fla.utils wrappers, and a fully fillable PR template cover the common cases copy-paste ready; the performance-evidence deferral to fla-nvidia-performance is an explicitly justified gap, so it stays at 5.	5 / 5
Workflow Clarity	A clear 7-step pre-flight sequence with a test-pass checkpoint and a flaky-test 'retry once' feedback loop plus documented CI enforcement matches 'Clear sequence with most checkpoints present; minor validation gaps'; not 5 because there is no single explicit gate before proceeding (e.g. 'only open the PR once steps 1-7 pass').	4 / 5
Progressive Disclosure	No bundle files exist, and the body is organized into clear sections with clearly signaled one-level-deep repo-file references (CONTRIBUTING.md, pull_request_template.md, check-pr-title.yml); the full PR template is inlined rather than split out, which is justified as the CI-enforced source of truth but keeps it at 'Good structure ... minor organization gaps' rather than 5.	4 / 5
	Total	17 / 20 Passed

Description

70%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, well-scoped to a single repo niche, and uses natural contributor vocabulary, but it omits an explicit 'Use when...' trigger clause, which caps its completeness. Adding a one-line trigger phrase would lift completeness without adding fluff.

Suggestions

Append an explicit trigger clause such as 'Use before opening a pull request or merge request in the FLA repo' to satisfy the 'when' half of completeness.

Spell out 'pull request / merge request' at least once alongside 'MR/PR' to broaden natural trigger-term coverage.

Optionally note 'code-style review' alongside the four coverage areas to close the minor specificity gap.

Dimension	Reasoning	Score
Specificity	Quotes 'CONTRIBUTING.md compliance, test plan, benchmark evidence, and PR body structure' — four named concrete coverage areas, matching the anchor 'Lists several specific actions; minor gaps in coverage'; not a 5 because coverage items like code-review or dependency-chain handling are absent.	4 / 5
Completeness	The 'what' is clear ('Checklist and workflow for preparing an MR/PR') but there is no explicit 'Use when...' trigger clause, so per the boundary guidance completeness is capped at 3 ('clear what but when is missing or only weakly implied').	3 / 5
Trigger Term Quality	Natural contributor terms appear ('preparing an MR/PR', 'test plan', 'benchmark evidence', 'PR body'), with the MR/PR pair covering both synonyms; matches 'Good keyword coverage; a few natural terms missing' rather than 3 (which would lack these variations) or 5 (which would add spelled-out 'pull request'/'merge request').	4 / 5
Distinctiveness Conflict Risk	Scoping to 'the FLA repo' with MR/PR-readiness triggers carves a clear niche with minimal overlap risk, matching 'Clear niche with distinct triggers; minimal conflict risk'; not downgraded since it would not fire for unrelated skills.	5 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: fla-org/flash-linear-attention
Path: .agents/skills/fla-mr-readiness/SKILL.md
Commit: f470469

Reviewed: 4 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.