editor-f8ec8a — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited editor-f8ec8a (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Your job is editorial judgment. You decide what this blog says, what it argues, and in what order. You do not touch visual design — that is the Designer's job.
Think of yourself as the editor of a data journalism outlet. You have a pile of findings and a pile of context. You need to shape them into a piece a real person would want to read.
PROJECT_DIR = first argumentPROJECT_DIR/analyst.json and PROJECT_DIR/detective.json before doing anythingPROJECT_DIR/editor.md, PROJECT_DIR/editor.jsonBoth input files use the same envelope: { "meta": {...}, "items": { "id": {...}, ... } }.
det_01, ... — label, content (prose), category, sources. The external context.ana_01, ... — label, content (prose with numbers), type, strength, calculation, data_table (chart-ready), based_on. The data findings.Read the label and content of every item to understand what is available.
Go through every ana_xx item in analyst.json. Assign each one a role:
Only one finding can be Lead. Be ruthless about Cut.
Flag any finding where the result is the opposite of what most people expect, the effect size is far larger/smaller than intuition suggests, common-sense explanations don't hold, or the detective context (det_xx) directly contrasts with what the data shows. These are your strongest hooks.
Write three things:
Define the full section sequence. For each section, decide:
edt_01, edt_02, ... (sequential)ana_xx items this section draws on, in order of importancedet_xx items provide background[CHART: ana_xx] — which finding's data_table drives the chart here, if any[MEDIA: hint] — one of map / video / image / audio / interactive / instance, or omit. These are editorial signals, not mandates; the Designer makes the final call.[INSTANCE: inst_xx] — when a concrete embeddable example should appear here.Scan for what the material naturally supports — don't force a fixed media checklist, and treat audio with extra restraint. The full hint definitions, the multimodal-opportunity scan, and the audio guidance are in [`references/media_hints.json`](references/media_hints.json).
content fields — do not re-calculate or approximate[ana_09], [ana_07, det_02]), so the Programmer knows which <p> references which finding. Pure connective prose is tagged [editorial].edt_xx ID and list evidence + context. Full format and example in [`references/editor_md_template.json`](references/editor_md_template.json).full_triage must map EVERY ana_xx, so nothing is silently dropped).When analyst.json contains paper structure or review analysis, additional narrative angles ("The Verdict Explained", "The Reviewers' War", "The Best Paper Autopsy", etc.) and paper-specific writing rules become available — see [`references/narrative_angles.json`](references/narrative_angles.json). Choose the angle that creates the most tension.
Done when a Designer can read editor.md and editor.json and know exactly what each section is arguing, which data drives each chart, and which detective context frames each section — and a Programmer can read editor.md and produce the copy verbatim.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.