CtrlK
BlogDocsLog inGet started
Tessl Logo

guidance-tracker

Track management guidance accuracy over time for a given company

61

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/daloopa/skills/guidance-tracker/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and well-structured with concrete formulas, functions, and citation formats, plus clear sequencing and validation checkpoints. The main weakness is mild verbosity — it could be tightened, especially the read-through examples in section 7.5.

Suggestions

Tighten section 7.5: one detailed read-through example would convey the format; the second (TSMC) example and surrounding commentary could be trimmed.

Condense analytical-commentary prose (e.g., credibility rationale in section 6 and signal framing in 7.5) into terse directives without losing the instruction.

Sections 2 and 7 overlap on search keywords; consider cross-referencing instead of restating to reduce redundancy.

DimensionReasoningScore

Conciseness

The body is dense with domain-specific operational guidance and avoids explaining basic concepts Claude already knows, but at ~140 lines it includes passages that could be tightened — notably the two detailed read-through examples in section 7.5 and some analytical-commentary prose — fitting 'mostly efficient but could be tightened.'

2 / 3

Actionability

Provides concrete, executable guidance throughout: specific functions (discover_companies), exact formulas (Beat/Miss % = (Actual - Guidance) / |Guidance| x 100), a copy-paste citation format, explicit file paths, and a worked quarter-mapping table, matching 'fully executable guidance; copy-paste ready.'

3 / 3

Workflow Clarity

A clearly numbered 8-step sequence with explicit validation checkpoints — a precondition check ('If no ticker or company is provided, ask for one before proceeding') and a search-retry feedback loop with fallback keywords in section 7 — matching 'clear sequence with explicit validation steps; feedback loops for error recovery.'

3 / 3

Progressive Disclosure

Well-signaled one-level-deep references to sibling files (../data-access.md, ../design-system.md) with specific section pointers, plus a well-organized numbered body and no nested-reference chains, matching 'clear overview with well-signaled one-level-deep references; easy navigation.'

3 / 3

Total

11

/

12

Passed

Description

57%Weight 40%Scale 1-3

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 identifies a specific analytical niche and uses natural terminology, but is thin on action breadth and omits any explicit 'when to use' trigger guidance. It would benefit from a 'Use when...' clause and broader keyword coverage.

Suggestions

Add a 'Use when...' clause stating when to invoke this skill (e.g., 'Use when analyzing a company's guidance track record, beat/miss history, or management credibility').

Broaden trigger terms to include common variations users would say, such as 'guidance track record', 'beat rate', 'outlook accuracy', and 'earnings guidance'.

List more concrete actions (e.g., 'compare guidance to actuals, compute beat/miss rates, and assess management credibility') to raise specificity above a single verb.

DimensionReasoningScore

Specificity

Names the domain ('management guidance accuracy over time for a given company') and one concrete action ('Track'), but lists only a single action rather than multiple specific actions, matching the 'names domain and some actions, but not comprehensive' anchor.

2 / 3

Completeness

States what the skill does ('Track management guidance accuracy over time for a given company') but provides no 'Use when...' clause or explicit trigger guidance; per the rubric a missing trigger clause caps completeness at 2.

2 / 3

Trigger Term Quality

Includes natural terms a user might say ('management guidance', 'guidance accuracy') but lacks common variations (e.g., 'guidance track record', 'beat/miss', 'outlook') and any trigger clause, fitting 'some relevant keywords but missing common variations.'

2 / 3

Distinctiveness Conflict Risk

Targets a specific niche (management guidance accuracy tracking) that is clearly distinguishable from general financial-analysis skills and unlikely to trigger for the wrong skill, matching the 'clear niche with distinct triggers' anchor.

3 / 3

Total

9

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
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.