inflection

Auto-detect biggest acceleration/deceleration inflections across all metrics

Quality

53%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/daloopa/skills/inflection/SKILL.md

Quality

Content

57%

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

The skill is a well-structured, mostly lean analytical workflow with strong progressive disclosure and concrete formulas, but it plateaus at the midpoint on conciseness, actionability, and workflow clarity due to minor explanatory padding, math-notation rather than executable code, and absent validation checkpoints.

Suggestions

Add an explicit validation checkpoint after pulling/computing data, e.g., verify series have sufficient non-null quarters before ranking and re-pull any sparse series, to close the feedback-loop gap.

Trim obvious glosses like 'Positive = accelerating, Negative = decelerating' and 'These are metrics that are improving faster than before' that restate what the formulas already show.

Optionally convert the growth/acceleration formulas into a short executable snippet (e.g., a pandas expression) so the computation is copy-paste ready rather than math notation.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and action-oriented with concrete formulas, but it includes obvious glosses Claude already knows ('Positive = accelerating, Negative = decelerating', 'These are metrics that are improving faster than before') that could be trimmed.	2 / 3
Actionability	Guidance is concrete and specific (named tool discover_companies, exact growth/acceleration formulas, thresholds like 'at least 5 quarters' and '< 1% of revenue', and a full HTML output template), but the formulas are math notation/pseudocode rather than executable code, so it stops short of copy-paste-ready.	2 / 3
Workflow Clarity	The 8-step sequence is clearly numbered and well-ordered, but there are no explicit validation/verification checkpoints; since the workflow batch-processes many series across 8 quarters, the missing feedback loop caps workflow clarity at 2 per the guidelines.	2 / 3
Progressive Disclosure	Content is organized into clear numbered sections and externalizes data-access/design-system detail into well-signaled, one-level-deep references ('read ../data-access.md', with section pointers), with no nested reference chains.	3 / 3
	Total	9 / 12 Passed

Description

50%

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 concisely names the skill's domain and core action but is uniformly at the midpoint: it lacks a 'Use when' trigger, offers only one action, and relies on semi-technical keywords. Adding explicit trigger guidance and a couple more concrete actions would lift every dimension.

Suggestions

Add a 'Use when...' clause naming natural triggers, e.g., 'Use when analyzing whether a company's metrics are accelerating or decelerating, or when the user asks about inflection points or momentum shifts.'

List a couple more concrete actions to raise specificity, e.g., 'Auto-detect the biggest acceleration/deceleration inflections across all metrics, rank them by magnitude, and summarize the trend narrative.'

Include common natural variations of the trigger terms ('inflection points', 'momentum', 'growth acceleration', 'trend change') so users' phrasings match the description.

Dimension	Reasoning	Score
Specificity	Names a concrete domain ('acceleration/deceleration inflections across all metrics') and one action ('Auto-detect'), but lists only a single action rather than multiple specific concrete actions, so it falls short of the score-3 anchor.	2 / 3
Completeness	It clearly states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance; per the judging guidelines, a missing trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like 'inflection', 'acceleration/deceleration', and 'metrics' are somewhat natural for a finance user but lean technical and omit common variations (e.g., 'growth', 'momentum', 'trend change'), matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The inflection-detection niche is fairly specific, but with no explicit trigger terms it could still overlap with other financial metric-analysis skills, fitting the 'somewhat specific but could still overlap' anchor.	2 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/daloopa/skills/inflection/SKILL.md
Commit: 11c74d6

Reviewed: 2 days 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.