CtrlK
BlogDocsLog inGet started
Tessl Logo

niche-signal-discovery

Deprecated alias. This skill was renamed to `deepline-scoring`. Use when a user or script still invokes `/niche-signal-discovery`: immediately load and follow the `deepline-scoring` skill instead. Triggers: ICP analysis, niche signals, won vs lost analysis, differential signals, signal discovery, ICP signal report, account scoring signals, lead scoring, first-party signals, buyer signals.

65

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 mostly well-executed alias skill: the redirect workflow and fallback path resolution are concrete and executable, and the structure is appropriately minimal. The main defect is the Quick Start block of CLI install/auth commands, which belongs in the target skill and contradicts the body's statement that it contains no instructions of its own.

Suggestions

Remove or relocate the Quick Start install/auth block: it is operational setup for the `deepline-scoring` skill, not the alias, and contradicts 'Do not answer from this file; it contains no instructions of its own.'

Clarify whether the Quick Start commands should ever be run from this alias (e.g., 'if the CLI is not yet installed, see the deepline-scoring skill for setup') so the agent knows how the section relates to the redirect workflow.

Give the alias a concrete removal condition or date ('It will be removed' is open-ended), so future readers know when the deprecation window ends.

DimensionReasoningScore

Conciseness

The redirect core is lean, but the Quick Start block (global npm install, sandbox registry fallback, `auth register --wait auto`, `auth wait`) is operational setup that belongs in the target skill and directly contradicts the body's own claim that it 'contains no instructions of its own'. This matches 'mostly efficient but includes some unnecessary explanation'; not 2 because the rest of the body is tight and the block is small.

3 / 5

Actionability

Guidance is concrete and executable: a copy-paste bash loop probing three exact candidate roots ('.skills/deepline-scoring', '.claude/skills/...', '.agents/skills/...') plus explicit loader-name invocation. Not 5 because the body never states when (or whether) the Quick Start commands should actually run relative to the redirect, leaving a gap between the setup section and the 'What to do' flow.

4 / 5

Workflow Clarity

The single-purpose redirect sequence is unambiguous (load target skill → 'tell the user once, in a single line' → continue with the request), with a fallback resolution path for loaders without name support. Not 5 because the unexplained Quick Start section sits outside the stated workflow, leaving unclear whether the agent should execute it before redirecting; not 3 because the redirect steps themselves are complete with no risky operations requiring validation.

4 / 5

Progressive Disclosure

The body is under 50 lines with no bundle files, organized into clear sections (Quick Start, What to do), and its single reference (the `deepline-scoring` entrypoint) is one level deep and clearly signaled — matching the simple-skill case for well-organized structure with no separate files needed.

5 / 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 for a rename-alias skill: it is explicit about what it does (redirect to `deepline-scoring`), when to use it (old-name invocations plus a rich natural-language trigger list), and keeps third-person voice with no fluff. The only weakness is trigger overlap with the canonical skill it points to, which is acceptable for an alias.

DimensionReasoningScore

Specificity

States its concrete role and action explicitly ('Deprecated alias. This skill was renamed to `deepline-scoring`... immediately load and follow the `deepline-scoring` skill instead'), matching 'lists several specific actions; minor gaps'. Not 5 because capability detail is intentionally delegated to the target skill, so coverage is not comprehensive within the description itself.

4 / 5

Completeness

Explicitly answers both what ('Deprecated alias... load and follow the `deepline-scoring` skill instead') and when ('Use when a user or script still invokes `/niche-signal-discovery`' plus a dedicated Triggers list), matching the anchor for clear and explicit what AND when with concrete trigger phrases.

5 / 5

Trigger Term Quality

The Triggers list gives good natural-phrase coverage with synonyms ('ICP analysis, niche signals, won vs lost analysis, differential signals, signal discovery, ICP signal report, account scoring signals, lead scoring, first-party signals, buyer signals'), matching 'good keyword coverage; a few natural terms missing'. Not 5 because a few plausible variations (e.g., win/loss review, deal analysis) are absent.

4 / 5

Distinctiveness Conflict Risk

Scoped to a deprecated alias with a clear niche (invocations of the old name), matching 'mostly distinct; minor overlap risk'. Not 5 because its broad trigger list (lead scoring, buyer signals) overlaps the canonical deepline-scoring skill's own triggers, though the redirect makes the conflict largely benign.

4 / 5

Total

17

/

20

Passed

Validation

100%

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
getaero-io/gtm-eng-skills
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.