skill-cost-projections

Project remaining workflow cost from per-phase averages — warns on budget ceiling overruns

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skill-cost-projections/SKILL.md

Quality

Content

85%

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

The body is highly actionable and well-structured, with executable code, explicit formulas, validation guards, and thorough error handling across a clear multi-step workflow. Its main weakness is repetitive display-example duplication that could be tightened for token efficiency.

Suggestions

Consolidate the repeated '💰 Spent: $2.40 | Est. remaining: $3.60 | Total: ~$6.00' display line — define the base format once and show only the per-case additions (ceiling warning, profile tip).

Merge the duplicate 'insufficient data (< 2 steps)' example blocks in Step 1 and Step 4 into a single canonical instance.

Move the step-count-by-workflow-type table to a short reference note rather than repeating the per-phase detail, to reduce inline token weight.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and task-focused, but the same display line ('💰 Spent: $2.40 \| Est. remaining: $3.60 \| Total: ~$6.00') is repeated across Steps 4-6 and the Complete Display Examples, and step-count tables/duplicate 'insufficient data' blocks could be consolidated — closer to the 'mostly efficient but could be tightened' anchor than the lean level-3.	2 / 3
Actionability	Provides fully executable bash (jq aggregation, bc arithmetic), explicit formulas, exact display formats, and concrete env-var thresholds (OCTO_BUDGET_CEILING, OCTO_COST_THRESHOLD default 5.00) — copy-paste ready guidance.	3 / 3
Workflow Clarity	A clear six-step sequence (collect → average → project → display → warn → suggest) with explicit checkpoints: the '2+ completed steps' minimum-data guard, the optional ceiling check, and the Error Handling section covering missing/corrupt metrics and zero remaining steps — matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	Content is organized into well-labeled sections (Overview, Steps 1-6, Integration, Error Handling) with no nested/deep references and one conceptual pointer to the codex-host-adapter at the top; as a single self-contained SKILL.md with no bundle files, navigation is straightforward.	3 / 3
	Total	11 / 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 conveys what the skill does concisely and in third person, but it omits an explicit 'Use when' trigger clause and lacks a broad set of natural trigger terms, capping most dimensions at 2. It is distinct enough to avoid broad conflicts but not maximally differentiated.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks about remaining workflow cost, projected spend, or budget ceiling overruns'.

Expand the capability list with a few more concrete actions (e.g. 'compute average per-step cost, display in HUD, suggest budget profile') to reach the specificity level-3 anchor.

Include natural user-facing phrasings like 'cost projection', 'how much will this run cost', and 'budget overrun' to improve trigger-term quality.

Dimension	Reasoning	Score
Specificity	Names the domain ('remaining workflow cost from per-phase averages') and a concrete action ('warns on budget ceiling overruns'), but does not list multiple distinct concrete actions like extracting, merging, or filling — closest to the 'names domain and some actions' anchor.	2 / 3
Completeness	Clearly states what the skill does but provides no explicit 'Use when...' trigger clause, so per the guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Contains relevant terms ('workflow cost', 'budget ceiling') but lacks the common natural phrasings a user would actually say ('how much will this cost', 'cost projection', 'budget'); not the level-3 broad coverage of natural terms.	2 / 3
Distinctiveness Conflict Risk	The 'per-phase averages' framing gives it a fairly distinct niche, yet generic cost/budget language could still overlap with other cost or budget skills rather than the clear-niche level-3 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: nyldn/claude-octopus
Path: .claude/skills/skill-cost-projections/SKILL.md
Commit: 9f39f0c

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.