CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

credentials

Instructions for handling API keys and credentials safely, verifying their presence, and prompting the user to add them if missing using a safe protocol.

Quality

66%

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 ./skills/credentials/SKILL.md
SKILL.md
Quality
Evals
Security

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 a well-structured, actionable protocol with copy-nearly-ready commands and a clear verify-then-prompt workflow. Its main weakness is repetition of the same critical instructions in multiple forms, which inflates length without adding guidance.

Suggestions

Consolidate the duplicated instructions: the [!CRITICAL] callout repeats the stop-and-prompt rule already stated in the bullet list, and the placeholder-replacement rules appear twice — state each once.

Add an explicit post-prompt step telling the agent to re-run the grep verification after the user confirms they added the credential.

Include one fully resolved example (e.g., with ALPHAGENOME_API_KEY and ~/.env substituted) to make the templates unambiguously copy-paste ready.

DimensionReasoningScore

Conciseness

The protocol is mostly lean with executable commands, but key instructions are duplicated — 'do not conclude the turn by simply reporting the missing key' appears in both the bullet list and the [!CRITICAL] callout, and the placeholder-replacement rules are stated twice (lines 37-38 and 68-74).

3 / 5

Actionability

Provides fully executable commands — `grep -sq "^CREDENTIAL_NAME=" ~/.env` and the complete printf/read -s append template — with explicit placeholder-replacement rules and concrete credential-name examples; the only minor gap is the absence of a fully resolved example command.

4 / 5

Workflow Clarity

The sequence is clear (verify with grep → branch on exit code → proceed or generate the prompt command from a template) with the exit-code check acting as an explicit checkpoint; it falls short of 5 only because there is no explicit re-verification step after the user adds the credential.

4 / 5

Progressive Disclosure

No bundle files exist or are needed for this self-contained protocol, and the body is well-organized into clear sections with a working internal anchor link; at ~89 lines it exceeds the under-50-line simple-skill exception, so structure is good but not exemplary.

4 / 5

Total

15

/

20

Passed

Description

50%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 communicates a clear purpose with a couple of concrete actions, but it is uniform mid-pack quality: no "when to use" guidance, limited trigger-term variety, and a vague "handling safely / safe protocol" framing. Adding explicit trigger conditions and natural synonyms would lift most dimensions.

Suggestions

Add a 'Use when...' clause (e.g., 'Use when a skill requires an API key or credential, or when the user mentions API keys, secrets, tokens, or .env files') to raise completeness and trigger-term quality.

Replace vague phrasing like 'handling API keys and credentials safely' and 'using a safe protocol' with the concrete mechanism (e.g., 'checks .env for credentials without printing values').

Include natural synonyms and file extensions users would say — 'secrets', 'tokens', '.env', 'environment variables' — to broaden trigger coverage.

DimensionReasoningScore

Specificity

The description names the domain and two concrete actions ("verifying their presence, and prompting the user to add them if missing"), but "handling API keys and credentials safely" is generic and coverage is not comprehensive (no mention of .env files, secrets, or environment variables).

3 / 5

Completeness

The "what" is clear (verify credential presence, prompt the user to add missing ones), but there is no "Use when..." clause or any explicit trigger guidance, capping completeness at 3.

3 / 5

Trigger Term Quality

"API keys" and "credentials" are relevant keywords, but common variations users would naturally say — "secrets", "tokens", "API key", ".env", "login" — are missing.

3 / 5

Distinctiveness Conflict Risk

The credentials/API-key niche is somewhat specific, but many skills involve API keys and the description offers no distinct trigger phrases to reduce overlap risk with related skills.

3 / 5

Total

12

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

google-deepmind/science-skills

Path

skills/credentials/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.