Tessl • The management layer for AI agent skills

SkillPublic

system-history

Blobless-safe git and PR history for this repo. Collects first-parent commits, scores systems against the repo's own baseline to separate fragile from fast-moving, lists recent changes to specific files as regression candidates, and reads PR diffs through GitHub. Use when you need to know how an area has been changing, what recently touched a file, or what a PR did.

Quality

89%

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

Quality

Content

86%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 tight, highly actionable skill body that documents each bundled script with its flags, exit codes, and a validation-first entry point, while explaining only the non-obvious repo-specific constraints. Its main gaps are a templated rather than literal example invocation and an implicitly rather than explicitly stated collect-to-analyze sequence.

Suggestions

Add one fully literal end-to-end example (e.g., `pnpm exec tsx $H/analyze.ts --run <id> --focus src/foo.ts --regression-days 30`) so the templated invocation pattern becomes copy-paste ready.

Make the doctor -> collect -> analyze -> pr sequence explicit as a numbered workflow in the intro, rather than relying on the order of the Scripts list.

Dimension	Reasoning	Score
Conciseness	Lean and dense with zero padding; the blobless-clone warning ("git show, git diff, git log -p ... fetch blobs one at a time and stall") is repo-specific, non-obvious, and load-bearing rather than background explanation.	5 / 5
Actionability	Provides a concrete run command and per-script flags (--lookback-days, --focus, --regression-days, --pr N), but the entry command is a template ("tsx $H/<script>.ts --run <id> [...]") with no fully literal end-to-end example.	4 / 5
Workflow Clarity	Sequence is present in listing order with a validation checkpoint (doctor.ts verifying base branch and gh auth), documented exit codes, and a re-run feedback loop ("re-run analyze.ts without collecting again"), but the collect-to-analyze ordering is implicit rather than explicit numbered steps; operations are read-only so the destructive/batch cap does not apply.	4 / 5
Progressive Disclosure	Short, well-sectioned overview with the scripts living as real files in the bundle (scripts/doctor.ts, collect.ts, analyze.ts, pr.ts, lib.ts all exist) and external pointers (fragility-common, refactor-plan rubric) clearly signaled and one level deep.	5 / 5
	Total	18 / 20 Passed

Description

92%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 third-person, action-dense, and explicitly scoped, covering what the skill does and when to use it with concrete trigger phrases. Its only weakness is missing a few common synonym triggers (e.g., "git log", "blame", "recent commits") that users might naturally say.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — "Collects first-parent commits", "scores systems against the repo's own baseline to separate fragile from fast-moving", "lists recent changes to specific files as regression candidates", and "reads PR diffs through GitHub" — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what (four concrete capabilities) and when ("Use when you need to know how an area has been changing, what recently touched a file, or what a PR did") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural phrases ("how an area has been changing", "what recently touched a file", "what a PR did") but misses common variations users would say such as "git log", "blame", or "recent commits".	4 / 5
Distinctiveness Conflict Risk	Clear niche — blobless-clone-safe repo history analysis with system fragility scoring and regression candidates — with distinct triggers that minimal generic git skills would claim.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: BuilderIO/agent-native
Path: .agents/skills/system-history/SKILL.md
Revision: 46ed84c

Reviewed: 19 days ago

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.

system-history

Table of Contents

Is this your skill?