eiirp

Everything In Its Right Place. The universal post-work organizer. After any significant work session, EIIRP runs a 7-phase audit: (1) inventory every output, (2) walk taxonomy to decide where each lands, (3) check schema-pack consistency against the brain's actual shape, (4) file enriched brain pages, (5) audit the skill graph for DRY+MECE, (6) verify resolvability, (7) report. Named after the Radiohead song. Nothing produced during significant work lives only in chat — knowledge becomes permanent, patterns become reusable. Also carries the always-on auto-fire gate: when >=500 words of structured analysis on a user-shared document is about to be delivered, file the brain page first, then deliver the analysis with the link in that same reply.

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/eiirp/SKILL.md

Quality

Content

70%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 delivers a clearly sequenced, well-validated 7-phase workflow with concrete gbrain commands and gating rules for risky operations — workflow clarity is excellent. Its main costs are duplication (the Phase 7 report block appears twice; Hard Rules restate Anti-Patterns), non-operational padding (epigraph, changelog), and a monolithic structure with references to external files that are not part of the bundle.

Suggestions

Deduplicate the Phase 7 report template: keep it once in 'Output Format' (or once in Phase 7) and reference the other section instead of repeating the full markdown block verbatim.

Move the changelog, the auto-fire-gate detail (exemptions, first-fire notice, storage policy), and the anti-patterns/hard-rules merge into a reference file (e.g. references/auto-fire-gate.md), leaving SKILL.md a concise overview with well-signaled one-level-deep links.

Tighten abstract steps with the concrete command forms already used elsewhere — e.g. give the actual gbrain command for 'append Timeline entry' (add_timeline_entry / add_timeline_entry tooling) and replace pseudo-paths like 'reference/.../page.md' with a real schema-pack-derived example.

Dimension	Reasoning	Score
Conciseness	The Phase 7 report template is duplicated almost verbatim between 'Phase 7: REPORT' and 'Output Format', and 'Hard Rules' restates the 'Anti-Patterns' section ('Auto-applying low-confidence schema suggestions' vs 'Schema changes require confirmation'); the changelog and the Radiohead epigraph add no operational value. Not 2 because the bulk of the body is operational instruction, not explanation of concepts Claude already knows.	3 / 5
Actionability	Concrete copy-paste commands throughout: 'gbrain schema show --json', 'gbrain capture --file <analysis.md> --slug <taxonomist-path>', 'gbrain check-resolvable', 'gbrain doctor --json', plus manifest and report templates. Not 5 because several steps remain abstract ('update State, append Timeline entry citing this research') and the filing-plan table uses pseudo-paths like 'reference/.../page.md'.	4 / 5
Workflow Clarity	Seven explicitly sequenced phases with explicit validation checkpoints: Phase 4c 'Verify every link resolves', the Phase 6 confirmation checklist, and the Phase 3 confidence floor ('when gbrain schema suggest returns confidence < 0.6... DO NOT auto-apply') that gates destructive schema writes. Matches the clear-sequence-with-validation-and-checklists anchor exactly.	5 / 5
Progressive Disclosure	A monolithic ~530-line body: the full auto-fire gate section, the changelog, and the anti-patterns are inline material that would fit separate reference files, and cross-references like '../conventions/brain-first.md', 'skills/brain-taxonomist/SKILL.md', and '_brain-filing-rules.md' point to files not present in the bundle (no references/, scripts/, or assets/ directories exist). Not 4 because no bundle structure exists to absorb the overflow and the referenced paths are unverifiable at read time.	3 / 5
	Total	15 / 20 Passed

Description

68%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 highly concrete, enumerating all seven phases of the audit plus the auto-fire gate condition in third person. Its weaknesses are the absence of explicit 'Use when...' trigger phrasing (the natural trigger phrases live in frontmatter triggers, not the description), an over-claiming 'universal' scope that raises conflict risk with adjacent brain-filing skills, and trivia ('Named after the Radiohead song') that pads without informing.

Suggestions

Add an explicit 'Use when...' clause to the description with the natural trigger phrases users actually say (e.g. 'Use when the user says organize this, put this in the brain, make this re-doable, or DRY this up, after a deep research thread or build session').

Trim non-informing trivia ('Named after the Radiohead song') and soften the over-claim 'The universal post-work organizer' to a scoped claim like 'The post-work organizer for gbrain brains' to reduce trigger overlap with ingestion and filing skills.

State the boundary inline in one clause (e.g. 'Does not handle new external content — that routes to ingest/media-ingest; per-page classification is brain-taxonomist') so the description alone distinguishes EIIRP from its neighbors.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions with comprehensive coverage: 'runs a 7-phase audit: (1) inventory every output, (2) walk taxonomy to decide where each lands... (5) audit the skill graph for DRY+MECE, (6) verify resolvability, (7) report'. The small trivia ('Named after the Radiohead song') does not reduce the action-level concreteness, which matches the comprehensive anchor rather than the 'minor gaps' anchor below it.	5 / 5
Completeness	The 'what' is explicit (the enumerated 7-phase audit) and the 'when' is present ('After any significant work session' plus the '>=500 words of structured analysis on a user-shared document' gate condition), so it rises above the missing-'when' cap of 3. Not 5 because there is no explicit 'Use when...' clause with concrete user-side trigger phrases.	4 / 5
Trigger Term Quality	Contains some relevant keywords ('EIIRP', 'post-work organizer', 'file the brain page') but the natural phrases users would say ('organize this', 'put this in the brain', 'make this permanent', 'archive this research') are only in the triggers frontmatter, not the description itself. Not 4 because a user reading only the description would not hit the common variations or synonyms.	3 / 5
Distinctiveness Conflict Risk	The 'universal post-work organizer' framing and 'file the brain page first' behavior overlap significantly with ingestion/taxonomist/filing skills, and 'universal' is an over-claim that invites misfires on any filing request. Not 4 because the post-work-session + 7-phase framing still gives it a recognizable niche distinct from single-purpose ingestion pipelines.	3 / 5
	Total	15 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (531 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	12 / 16 Passed

Repository: garrytan/gbrain
Path: skills/eiirp/SKILL.md
Commit: e78f1c3

Reviewed: 5 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.