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

75%

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 content is a well-sequenced, highly actionable orchestration skill with strong validation checkpoints and feedback loops across its 7 phases and auto-fire gate. Its weaknesses are verbosity from duplicated report/anti-pattern/hard-rules blocks and a lack of in-skill bundle files for progressive disclosure, leaning heavily on external sibling-skill paths.

Suggestions

De-duplicate the Phase 7 report and the Output Format block (currently near-identical) into a single template, and collapse Hard Rules that merely restate phase guidance.

Move the long anti-patterns list and the per-sibling-skill routing detail into a references/ file (e.g., references/filing-rules.md) referenced one level deep from the body to improve progressive disclosure.

Verify the external paths referenced in the body (../conventions/brain-first.md, skills/brain-taxonomist/SKILL.md, etc.) resolve, and consider noting which are required vs optional so Claude can degrade gracefully when a sibling skill is absent.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence (no basic-concept padding), but at ~450 lines it repeats material — the Phase 7 report appears twice near-verbatim, the auto-fire gate and anti-patterns restate the same filing exemptions, and several 'Hard Rules' duplicate phase guidance, so it could be tightened meaningfully.	3 / 5
Actionability	Concrete executable commands are provided throughout — 'gbrain schema show --json', 'gbrain capture --file <analysis.md> --slug <taxonomist-path>', 'gbrain check-resolvable', 'gbrain doctor --json' — with templates and manifest formats; minor gaps are the placeholder-heavy filing-plan table and reliance on invoking other skills (brain-taxonomist, skillify) for the actual write steps.	4 / 5
Workflow Clarity	The 7 phases are explicitly sequenced with validation checkpoints — Phase 6 runs check-resolvable/doctor/orphans and a checkbox confirmation list, the schema phase enforces a confidence < 0.6 human-in-the-loop gate, and the auto-fire gate has clear fire/no-fire conditions plus a first-fire notice feedback loop, satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	Structure is good (clear sections, consistent templates) but no bundle files exist in references/, scripts/, or assets/, while the body references many sibling skill paths (brain-taxonomist, brain-link-discipline, meeting-ingestion, etc.) and a conventions/brain-first.md doc that are external to this skill; most detail is inlined rather than split into one-level-deep reference files, so navigation relies on out-of-skill links.	3 / 5
	Total	15 / 20 Passed

Description

80%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 and comprehensive, clearly conveying both the 7-phase post-work audit and the always-on auto-fire gate in third person. Its main weakness is that the 'when to use' guidance and natural trigger phrases live in separate frontmatter fields rather than being explicitly integrated into the description prose.

Suggestions

Weave a 'Use when...' clause with concrete natural trigger phrases (e.g., 'organize this', 'DRY this up', 'make this re-doable') directly into the description so completeness and trigger-term quality are self-contained.

Briefly note the distinction from sibling skills inside the description (e.g., 'orchestrates the full post-work lifecycle, unlike single-page filers') to lower conflict risk without relying on the distinct_from field.

Tighten the auto-fire-gate sentence; the '> =500 words' threshold is useful but the surrounding clause is long and dilutes the core 'file first, then deliver' message.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'inventory every output', 'walk taxonomy to decide where each lands', 'check schema-pack consistency', 'file enriched brain pages', 'audit the skill graph for DRY+MECE', 'verify resolvability', 'report' — giving comprehensive coverage of the 7-phase audit plus the auto-fire gate.	5 / 5
Completeness	The 'what' is explicit and detailed (7-phase audit, auto-fire gate), and 'when' is present ('After any significant work session', 'when >=500 words of structured analysis... is about to be delivered'), but the when-clause could be more explicit and tied to concrete trigger phrases inline rather than relying on the separate triggers list.	4 / 5
Trigger Term Quality	Natural phrases like 'organize all of this work', 'make this re-doable', 'DRY this up', 'file this properly' appear in the triggers list rather than woven into the description itself; coverage is good but several natural synonyms live outside the description field.	4 / 5
Distinctiveness Conflict Risk	Clear niche as a post-work organizer with a distinct 7-phase lifecycle and the named auto-fire gate; minor overlap risk with related skills (brain-taxonomist, ingest, skillify) which are explicitly distinguished in the distinct_from field, though those distinctions are not in the description itself.	4 / 5
	Total	17 / 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: 9dadfb9

Reviewed: 2 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.