rules-management

Manage project-level agent behavioural rules recorded in a single rules file. Use when the user says 'new rule', 'add a rule', 'record that', 'make a rule that', 'note this', 'take note of', 'new instruction', or asks to codify an agent directive. Read the rules file to check existing rules before adding a new one. DO NOT use for ephemeral notes, one-off instructions, or instructions that belong in the project's own agent-facing docs. Triggers: 'new rule', 'add a rule', 'record that', 'make a rule', 'codify this', 'rule about', 'create a directive', 'note this', 'take note of', 'new instruction'.

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 ./skills/agentic-harness/rules-management/SKILL.md

Quality

Content

67%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 is highly actionable — real, verified commands and script paths, an explicit numbered workflow with a validation checkpoint, and well-signaled one-level-deep references. The main cost is redundancy: validation instructions and trigger lists are repeated multiple times, and the yq dependency behind the preferred generate path is undocumented, which slightly undermines both conciseness and executability.

Suggestions

State the validation command once (e.g., in Quick Start) and reference it from 'When to Use' and 'Rule Format' instead of repeating it verbatim three times; likewise drop the trigger-phrase list from the body since the frontmatter description already carries it.

Add `yq` to the Prerequisites section (the script's `generate` mode hard-fails without it) or provide a hand-written entry fallback when yq is unavailable.

Add one line of error-recovery guidance for the workflow's final step: what to do and re-check when `validate-rules.sh validate` reports a malformed entry.

Dimension	Reasoning	Score
Conciseness	Mostly on-point with no explanations of concepts Claude already knows, but noticeably repetitious: the validation command is spelled out three times (Quick Start, "When to Use" step 5, and the "Rule Format" section), the trigger list duplicates the frontmatter description, and the "When to Use" section restates the description's triggers. Fits anchor 3 ('could be tightened'); not 2 because every repetition is short and functional rather than padded prose.	3 / 5
Actionability	Gives copy-paste-ready commands ("./scripts/validate-rules.sh validate .claude/RULES.md", "./scripts/validate-rules.sh generate \"<title>\" \"<directive>\" \"<rationale>\"") and an exact rule-entry template, all matching the real script's usage. Not 5 because the recommended `generate` path silently depends on `yq`, which the script requires but the Prerequisites section never mentions — a real executable gap in the common case.	4 / 5
Workflow Clarity	A clear 5-step numbered sequence ("1. Read the existing rules file first... 5. Confirm by running scripts/validate-rules.sh validate") with an explicit validation checkpoint and a duplicate-check guard before the write. Not 5 because there is no error-recovery loop (what to do when `validate` fails), and not 3 because validation is explicit and sequenced rather than implicit or absent.	4 / 5
Progressive Disclosure	All four referenced bundle paths are real (references/rule-format.md, scripts/validate-rules.sh, assets/schemas/rule-entry.schema.json, assets/templates/rule-entry.yaml), one level deep, and clearly labeled in a closing References section. Not 5 because the inline "Rule Format" section duplicates content that also lives in references/rule-format.md — a minor organization gap rather than a clean overview-only split.	4 / 5
	Total	15 / 20 Passed

Description

86%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 with explicit what/when structure, an explicit negative scope boundary, and unusually thorough natural-language trigger coverage. The main weakness is that the capability statement leans on the generic verb "Manage" with only a couple of concrete actions spelled out, and a few of the trigger phrases are generic enough to risk overlap with note-capture skills.

Dimension	Reasoning	Score
Specificity	Names the domain ("project-level agent behavioural rules recorded in a single rules file") and a couple of concrete actions ("Read the rules file to check existing rules before adding a new one"), but the core action verb "Manage" is generic and the action list is not comprehensive. Fits anchor 3 better than 4 because only 1-2 concrete actions are explicit rather than 'several specific actions'.	3 / 5
Completeness	Explicitly answers both: what ("Manage project-level agent behavioural rules recorded in a single rules file... Read the rules file to check existing rules before adding a new one") and when ("Use when the user says 'new rule', 'add a rule', ..." plus an explicit DO-NOT-USE boundary). Matches the anchor-5 example structure of concrete capabilities followed by explicit trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-language coverage with many synonyms: "'new rule', 'add a rule', 'record that', 'make a rule', 'codify this', 'rule about', 'create a directive', 'note this', 'take note of', 'new instruction" — these are exactly the phrasings a user would say. Matches the anchor-5 example's breadth of synonyms; not 4 because no common variation is obviously missing.	5 / 5
Distinctiveness Conflict Risk	The rules-file niche is mostly distinct with clear triggers, but generic capture phrases like "note this", "take note of", and "record that" carry real overlap risk with note-taking/memory skills. Not 5 because of that overlap; not 3 because the DO-NOT clause ("DO NOT use for ephemeral notes, one-off instructions") explicitly fences off the nearest conflicting territory.	4 / 5
	Total	17 / 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: 2 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 4 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: pantheon-org/tekhne
Path: skills/agentic-harness/rules-management/SKILL.md
Commit: a1083f4

Reviewed: 3 hours 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.