CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

secret-handling

Never read .env files or write secrets to .squad/ committed files

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/secret-handling/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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 an unusually actionable policy skill: exact file lists, a scannable regex table, executable PowerShell validation code, copy-paste alert templates, and two clearly sequenced workflows with explicit validation and fail-loud checkpoints. Its main weakness is redundancy — patterns and rules are repeated across the table, the code example, and the Anti-Patterns section — and its length suggests the pattern library could be split into a reference file.

Suggestions

Deduplicate the secret patterns: keep them in the regex table only and have the PowerShell example reference the table (or include all 7 patterns in the code) instead of repeating 3 of them.

Trim the Anti-Patterns section to only the cases not already covered in Patterns (e.g., keep "extracting just the host" and "temporary files") to cut repeated rules.

DimensionReasoningScore

Conciseness

The body is mostly directives, tables, and templates with no explanation of concepts Claude already knows, but there is real duplication: the regex patterns appear in the scanning table and again (3 of 7) in the PowerShell example, and the Anti-Patterns section restates rules already covered in Patterns. This matches anchor 3 (mostly efficient but could be tightened) rather than anchor 2, since there is no concept-level padding.

3 / 5

Actionability

Guidance is highly concrete — exact prohibited/allowed file lists, a 7-row regex table, copy-paste report templates, and executable PowerShell with real git commands (git reset HEAD <file>, git filter-repo). The minor gap keeping it below anchor 5 is that the example scanning code implements only 3 of the 7 table patterns, so it is not fully copy-paste ready on its own.

4 / 5

Workflow Clarity

Both workflows (pre-commit validation and leak remediation) are numbered with explicit validation checkpoints, a STOP/block/exit error path, and a fix-and-retry feedback loop ("remove the secret, replace with placeholder, and try again"), plus an explicit ordering note ("AFTER staging files, BEFORE calling git commit"). Validation is present, so the destructive-operation cap does not apply; this matches the anchor-5 example of clear sequence with explicit validation and error-recovery loops.

5 / 5

Progressive Disclosure

Sections are well organized (Context, Patterns, Examples, Anti-Patterns) with no nested or buried references, but at roughly 190 lines the regex pattern library and remediation scripts are content that could live in a separate reference file. Anchor 4 (good structure, most content appropriately placed, minor organization gaps) fits; anchor 5's under-50-line simple-skill exception does not apply.

4 / 5

Total

16

/

20

Passed

Description

53%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 precise and highly specific for what it states, naming exact file targets (.env, .squad/) and two absolute prohibitions, but it reads as a policy statement rather than a capability description. It lacks any "Use when..." trigger guidance and misses both common synonym terms (credentials, API keys, tokens) and the skill's active capabilities (pre-commit scanning, commit blocking, leak remediation).

Suggestions

Add an explicit trigger clause, e.g. "Use when handling configuration, credentials, or environment variables, or before committing .squad/ files."

Broaden trigger terms to include natural synonyms users would say: "credentials", "API keys", "tokens", "secrets leak", and ".env.local" / ".env.production" variants.

Mention the skill's active capabilities (pre-commit secret scanning, commit blocking, leak remediation steps) so the description covers more of what the skill actually does.

DimensionReasoningScore

Specificity

"Never read .env files" and "write secrets to .squad/ committed files" are two concrete, named actions, but coverage is not comprehensive — the description omits the pre-commit scanning, commit-blocking, and remediation capabilities the body documents. Anchor 3 (1-2 concrete actions, not comprehensive) fits better than anchor 4, which requires several actions.

3 / 5

Completeness

The "what" is clear (two absolute prohibitions), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines. Not anchor 4, which requires both what and when to be present.

3 / 5

Trigger Term Quality

Relevant natural keywords are present (" .env files", "secrets", "committed files"), but common variations users would say are missing: "credentials", "API keys", "tokens", "leak", or ".env.local". This matches anchor 3 (some relevant keywords, missing common variations) rather than anchor 4's good coverage.

3 / 5

Distinctiveness Conflict Risk

The ".squad/ committed files" phrase carves a precise team-workflow niche with distinct triggers (.env, secrets), but "Never read .env files" could overlap with a general security or credential-hygiene skill. Anchor 4 (mostly distinct, minor overlap risk with closely related skills) is the best fit; anchor 5 would require fully distinct triggers with minimal conflict risk.

4 / 5

Total

13

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

microsoft/waza

Path

.github/skills/secret-handling/SKILL.md

Reviewed

Table of Contents

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.