aif-warmup

Load the essential AI Factory project context before work begins. Reads configured DESCRIPTION, ARCHITECTURE, ROADMAP, RESEARCH, RULES, and applicable AGENTS.md files, then returns a compact session handoff suitable for continuing or forking. Use at the start of a new session or after context loss.

Quality

79%

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 ./skills/aif-warmup/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.

A well-crafted, disciplined instruction-only skill: every line is a rule, the workflow is clearly sequenced with explicit handling of missing or malformed inputs, and boundaries are unambiguous. It consistently lands just below the top anchors due to minor verbosity in the warmup.paths section and a few soft judgment-call criteria.

Suggestions

Move the detailed warmup.paths edge-case rules (~20 lines: symlink, binary, secrets, and large-directory handling) into a references/ file and keep a 3-4 line summary in SKILL.md, improving both conciseness and progressive disclosure.

Replace soft thresholds like "too large to load without crowding out the handoff" with a concrete limit (e.g. a line or byte count) so the guidance is fully executable.

Tighten the repeated "report and skip/report it" phrasing in the warmup.paths section into a single stated principle (e.g. "any skipped or failed entry is named in the handoff") applied once.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely prescriptive directives ("Use the nearest ancestor containing `.ai-factory/` as the project root"; "`rules.<area>` > `rules.base` > `paths.rules_file`") with no explanation of concepts Claude already knows. Minor tightening is possible — the warmup.paths section repeats "report and skip/report it" phrasing and enumerates edge cases exhaustively — so it is efficient-with-minor-trimmings rather than maximally lean.	4 / 5
Actionability	Guidance is highly concrete for an instruction-only skill: exact config keys with documented defaults, an ordered read sequence, and the exact marker `<!-- aif:research-mode:ultra -->`. A few judgment-call phrases ("too large to load without crowding out the handoff", "cannot be parsed confidently") leave minor gaps, keeping it below the fully copy-paste-ready anchor.	4 / 5
Workflow Clarity	Steps 0–3 are clearly sequenced with explicit failure handling at each stage ("If config cannot be parsed confidently, report that and use defaults"; "Record them as missing and continue"; "Report the skipped path"). The skill is read-only so no destructive/batch validation cap applies, but error handling is report-and-continue rather than explicit validate→fix→retry loops, matching the 4 anchor.	4 / 5
Progressive Disclosure	The skill is self-contained with no bundle files (no references/, scripts/, or assets/ exist) and clean section organization (Steps 0–3, Artifact Ownership, Boundaries). It exceeds 50 lines and the ~20-line warmup.paths edge-case rules could plausibly live in a separate reference file, so structure is good but not optimal.	4 / 5
	Total	16 / 20 Passed

Description

83%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.

A strong description: concrete actions, explicit "Use when..." triggers, and a clear project niche. Trigger coverage and distinctiveness fall just short of the top anchors due to missing natural synonyms and a somewhat broad "new session" trigger.

Dimension	Reasoning	Score
Specificity	"Reads configured DESCRIPTION, ARCHITECTURE, ROADMAP, RESEARCH, RULES, and applicable AGENTS.md files, then returns a compact session handoff" lists several concrete, specific actions with named inputs. It sits at the 'several specific actions; minor gaps' anchor rather than 5 because the action set reduces to reading files and producing a summary without finer-grained capabilities.	4 / 5
Completeness	It clearly answers both questions: the "what" ("Reads configured ... files, then returns a compact session handoff") and an explicit "Use at the start of a new session or after context loss" clause with concrete trigger phrases. This matches the top anchor exactly; score 4 would require a less explicit 'when'.	5 / 5
Trigger Term Quality	"start of a new session", "after context loss", "project context", and "session handoff" are natural phrases a user would say. A few natural variations (e.g. "onboard", "get up to speed", "resume session") are missing, so it matches the good-but-not-comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	The "AI Factory project context" niche and specific artifact names make it mostly distinct with minimal conflict risk. It is not a 5 because "start of a new session" is a fairly broad trigger that generic session-setup or context-loading skills could also claim.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: lee-to/ai-factory
Path: skills/aif-warmup/SKILL.md
Commit: ac92beb

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.