Name: write-spike
Rating: 68.8 (1 reviews)
Author: AndreJorgeLopes

write-spike

Use when starting a new initiative spike, investigating technical feasibility, assessing impact across services, or writing an engineering discovery document — produces a structured spike doc with diagrams and a private notes file.

Quality

86%

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

The canonical home for this skill is write-spike in AndreJorgeLopes/devflow

Quality

Content

77%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 well-engineered process skill: unambiguous sequencing, explicit validation checkpoints, and highly specific guidance that assumes Claude's competence. Its main weaknesses are a broken/unverifiable set of file references (the spike template and config example are absent from the bundle) and some inlined detail plus mild redundancy that could be trimmed or split out.

Suggestions

Ship the referenced bundle files: spike-template.md, company-config.example.yaml, and requirements.json are cited as REQUIRED but are absent from the skill directory, leaving Phase 3 without its template.

Move the detailed procedures (e.g., 2.4 Database Impact Analysis, the Nimbalist task-file format) into a one-level-deep reference file, keeping SKILL.md as the overview with clearly signaled links.

Trim or merge the Red Flags table into the phases it restates, and compress the preflight/eval-mode sections to cut token cost without losing the behavior gates.

Dimension	Reasoning	Score
Conciseness	Dense, imperative prose that assumes competence (e.g., "PG11+ ADD COLUMN WITH DEFAULT, CREATE INDEX CONCURRENTLY, pg_repack, gh-ost") with no re-teaching of known concepts. The Red Flags table partially restates mandates already given ("Multi-source always", "Always two files"), and the preflight/eval-mode sections could be tightened, so not 5.	4 / 5
Actionability	Concrete, executable guidance throughout: named subagent assignments, exact user prompts ("Continue here or start fresh?"), precise file-naming patterns (".<date>-<slug>.private.md"), and a 10-row quality-gates table. Minor gaps — e.g., no example format for the Nimbalist task files — keep it below fully copy-paste-ready.	4 / 5
Workflow Clarity	Four clearly sequenced phases with a Mermaid flowchart, an explicit "Every phase is mandatory" mandate, a scope-check decision point with quantified thresholds ("30+ spike goals", "15 goals AND 6 external dependencies"), and explicit validation loops (self-review "Fix inline", grill-me pass, quality gates). Publishing is gated ("Never auto-publish"), matching the top anchor's explicit checkpoints and error-recovery loops.	5 / 5
Progressive Disclosure	The core template is delegated to "spike-template.md" ("REQUIRED REFERENCE") and config to "company-config.example.yaml", but none of the referenced files — including "requirements.json" — exist in the skill's bundle, so the references are unverifiable/broken. Additionally, Phase 2 detail (e.g., the full DB impact analysis procedure) is inlined where a reference file would fit, matching the "some structure" anchor rather than good structure.	3 / 5
	Total	16 / 20 Passed

Description

87%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: explicit "Use when" triggers covering multiple natural entry points, concrete third-person outputs, and a well-defined niche. Only minor gaps in action coverage and trigger synonym breadth keep specificity and trigger quality at 4.

Dimension	Reasoning	Score
Specificity	Names concrete outputs — "produces a structured spike doc with diagrams and a private notes file" — plus specific activities like "investigating technical feasibility" and "assessing impact across services". Falls short of 5 because it doesn't enumerate what the produced document covers, and exceeds 3's 1-2 action bar.	4 / 5
Completeness	Opens with an explicit "Use when" clause listing multiple concrete triggers and closes with a clear third-person statement of what it does. Both "what" and "when" are explicit with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Natural phrases users would say — "initiative spike", "technical feasibility", "engineering discovery document" — with synonym coverage across "spike"/"discovery". A few natural variations (e.g., "RFC", "proof of concept", "investigate impact on <service>") are missing, so not 5.	4 / 5
Distinctiveness Conflict Risk	"Initiative spike" and "engineering discovery document" carve a clear niche with distinct triggers; unlikely to collide with general writing or research skills. Not 4 because overlap risk is minimal rather than minor.	5 / 5
	Total	18 / 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: AndreJorgeLopes/devflow
Path: devflow-plugin/skills/write-spike/SKILL.md
Commit: bd4b70c

Reviewed: 7 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.