skill-cost-projections

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

Quality

60%

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 ./skills/skill-cost-projections/SKILL.md

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 concrete, executable six-step procedure with strong display examples and real error handling — a solid, usable instruction set. Its weaknesses are redundancy (formula blocks duplicating bash, repeated example sections), an unsourced `total_steps` variable, and a dangling reference to a host-adapter file that is not part of the bundle.

Suggestions

Drop the redundant "Formula" blocks in Steps 2–3 and the "Complete Display Examples" section, which repeat content already shown verbatim.

Define where `total_steps` comes from (e.g., a workflow-type lookup or `OCTO_TOTAL_STEPS`) and remove the unused `completed_costs` assignment.

Add an explicit validation/retry step for corrupted metrics (e.g., count skipped entries and fall back to HUD counters if fewer than 2 valid entries remain) rather than only instructing to "skip malformed entries".

Dimension	Reasoning	Score
Conciseness	Mostly efficient code-first structure, but it includes redundant material: Step 2's "Formula: avg_cost = total_cost / completed_steps" and Step 3's formula block restate the adjacent bash arithmetic, and "Complete Display Examples" repeats the exact display strings already shown in Steps 4–6.	3 / 5
Actionability	Concrete, executable jq/bc bash snippets, exact display formats, and guarded env-var checks make the guidance mostly copy-paste ready; minor gaps remain — `total_steps` in Step 3 is never sourced, and `completed_costs` is assigned but unused.	4 / 5
Workflow Clarity	Steps 1–6 are clearly sequenced with checkpoints (2-step minimum guard, corrupted-metrics fallback, zero-remaining-steps case) and an Error Handling section; falls short of a 5 because `total_steps` is undefined and there is no validate/retry loop for malformed data beyond "skip malformed entries".	4 / 5
Progressive Disclosure	A well-sectioned single file with one clearly signaled host reference ("see `skills/blocks/codex-host-adapter.md`"); not 5 because the body exceeds 50 lines with content that could split out (the workflow step-count table and the repeated display examples), and that referenced file does not exist in the skill's bundle.	4 / 5
	Total	15 / 20 Passed

Description

53%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 states two concrete, distinguishable capabilities in lean third-person voice, but it has no "Use when..." trigger guidance and only partial natural-keyword coverage, capping completeness and trigger quality. Adding a use-when clause naming workflow types (embrace, research, review, debate) and natural phrases like "how much will this cost" would lift it substantially.

Suggestions

Append a trigger clause, e.g. "Use when a workflow is in progress and the user asks about cost, budget, or projected spend."

Include natural synonyms users would say — "cost estimate", "projected total", "over budget" — alongside "workflow cost" and "budget ceiling".

Mention the HUD/statusline display and the metrics files it reads so the "what" matches the body's full capability set.

Dimension	Reasoning	Score
Specificity	Names the domain plus two concrete actions — "Project remaining workflow cost from per-phase averages" and "warns on budget ceiling overruns" — but omits other capabilities the body performs (HUD display, profile suggestions, insufficient-data handling), matching the 1-2-concrete-actions anchor rather than the several-actions anchor.	3 / 5
Completeness	The "what" is clear (project remaining cost, warn on overruns) but there is no "Use when..." clause or equivalent trigger guidance, which the rubric explicitly caps at 3.	3 / 5
Trigger Term Quality	"workflow cost" and "budget ceiling" are relevant keywords, but common natural phrasings users would say ("how much will this cost", "projected spend", "over budget", "cost estimate") are missing, so keyword coverage is partial without synonyms or variations.	3 / 5
Distinctiveness Conflict Risk	"per-phase averages" and "budget ceiling overruns" carve a fairly distinct niche with minor overlap risk against generic cost/budget skills; not 5 because the absence of explicit trigger phrases leaves some ambiguity against sibling cost/profile skills.	4 / 5
	Total	13 / 20 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: skills/skill-cost-projections/SKILL.md
Commit: 0093dab

Reviewed: 5 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.