Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jscraik/Agent-Skills --skill technical-writergit clone --depth 1 https://github.com/jscraik/Agent-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jscraik/agent-skills/technical-writer)<a href="https://agentmods.dev/skills/jscraik/agent-skills/technical-writer"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/technical-writer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jscraik/agent-skills/technical-writer"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/technical-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00063 | $0.01587 |
| Opus 5 | $0.00032 | $0.00794 |
| Sonnet 5 | $0.00013 | $0.00317 |
| Haiku 4.5 | $0.00006 | $0.00159 |
Grade A, and why
technical-writer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Writer
When To Use
- README, runbook, code-doc, template, config-doc, or trust-surface docs need audit or rewrite.
- Skill package evidence or runtime-boundary docs need proof-backed explanation.
- Claims need checks against scripts, commands, workflows, tests, repo structure, support paths, or governance docs.
- Generated, mirrored, registry, or publication docs need canonical ownership and reader-visible validation.
- Talks, articles, DevRel content, service content, visual docs, and short-form writing need evidence-backed technical shaping.
Inputs
Doc target, audience, reader job, writing mode, truth files, validation commands, glossary or ubiquitous-language surfaces, and brand/governance constraints.
Outputs
For audits and broad rewrites, return findings, claim/evidence map, ownership decisions, validation, unknowns, and handoff needs. For narrow corrections, return the corrected text or patch plus exact evidence. For editorial judgment, return verdict, central risk, revision direction, and a rewrite only when requested. Return no_justified_edit when documentation is not the safe owning surface.
Execution Boundaries
Inspect applicable instructions and preserve the current worktree before drafting. Edit only the canonical documentation owner. Treat generators, runtime or mirrored copies, registries, publication surfaces, user configuration, and external systems as separate lanes. Do not invent commands, paths, versions, access, platform behavior, or readiness claims. Do not change runtime behavior, dependencies, CI, release state, trackers, projections, or publication state without the owning workflow and approval.
Discovery interview
Inspect known, read-only surfaces without delay. When the editable boundary is materially unknown, ask one plain-language question before edits: ask which documentation surface to inspect, identify the canonical source path or editable owner, and block edits until that surface is chosen. For a staged package, ask for its source path or editable scope rather than guessing. Ask one round at a time, explain why this matters, and avoid dumping the full interview plan at once.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 184 B
- references/contract.yaml 10 KB
- references/discovery-interview.md 1.6 KB
- references/documentation-quality.md 12 KB
- references/eval-regression-plan.json 9.5 KB
- references/eval-scenarios.json 35 KB
- references/evals.yaml 74 KB
- references/evals/eval.glossary-workspace-authority.md 1.2 KB
- references/evals/eval.knowledge-os.capsule-design-without-relationships.md 1.9 KB
- references/evals/eval.knowledge-os.consumer-receipt-stale-digest.md 1.7 KB
- references/evals/eval.knowledge-os.export-pass-overclaims-quality.md 2.6 KB
- references/evals/eval.knowledge-os.skills-sdk-handoff-overclaims-ingest.md 1.9 KB
- references/evals/eval.reader-state-citation-map.md 1.1 KB
- references/evals/eval.validation-lane-separation.md 1.1 KB
- references/evals/eval.visual-evidence-decision.md 1.3 KB
- references/evals/eval.writer-gap-gathering.md 1.4 KB
- references/knowledge-capsule-routing.md 5.1 KB
- references/knowledge-capsule.manifest.yaml 24 KB
- references/knowledge-capsules/accessible-writing.md 7.3 KB
- references/knowledge-capsules/actionable-error-messages.md 8.5 KB
- references/knowledge-capsules/answer-first-argument-structure.md 9.8 KB
- references/knowledge-capsules/clarity-mechanics.md 6.8 KB
- references/knowledge-capsules/content-design-service-docs.md 8.9 KB
- references/knowledge-capsules/devrel-community-docs.md 8.1 KB
- references/knowledge-capsules/documentation-quality.md 15 KB
- references/knowledge-capsules/downstream-skill-routing.md 5.6 KB
- references/knowledge-capsules/revision-and-structure.md 7.0 KB
- references/knowledge-capsules/technical-explanation.md 7.6 KB
- references/knowledge-capsules/technical-writer-devrel-communication-accessible-and-inclusive-writing.md 7.4 KB
- references/knowledge-capsules/technical-writer-devrel-communication-articles-and-long-form.md 8.2 KB
- references/knowledge-capsules/technical-writer-devrel-communication-clarity-style-and-revision.md 9.0 KB
- references/knowledge-capsules/technical-writer-devrel-communication-content-design-and-service-docs.md 8.9 KB
- references/knowledge-capsules/technical-writer-devrel-communication-developer-education.md 7.7 KB
- references/knowledge-capsules/technical-writer-devrel-communication-devrel-role-and-audience.md 8.1 KB
- references/knowledge-capsules/technical-writer-devrel-communication-error-messages-and-recovery.md 8.5 KB
- references/knowledge-capsules/technical-writer-devrel-communication-presentations-and-visual-docs.md 9.1 KB
- references/knowledge-capsules/technical-writer-devrel-communication-short-form-and-content-creation.md 7.0 KB
- references/knowledge-capsules/technical-writer-devrel-communication-storytelling-and-explanation.md 9.8 KB
- references/knowledge-capsules/technical-writer-devrel-communication-technical-documentation.md 9.0 KB
- references/knowledge-capsules/technical-writer-devrel-communication-voice-signal-and-taste.md 6.7 KB
- references/knowledge-capsules/visual-document-structure.md 9.1 KB
- references/knowledge-demand.yaml 1.8 KB
- references/knowledge-os-capsule-design.md 19 KB
- references/knowledge-os-export-readiness.md 15 KB
- references/scorer-calibration/examples.jsonl 1.1 KB
- references/scorer-calibration/manifest.json 629 B
- references/scorer-calibration/raw/concise-correct-vs-verbose-wrong.json 199 B
- references/scorer-calibration/raw/copied-rubric-no-evidence.json 186 B
- references/scorer-calibration/raw/local-proof-overclaim.json 191 B
- references/scorer-calibration/raw/obvious-correct-doc-evidence.json 181 B
- references/scorer-calibration/raw/obvious-wrong-invented-command.json 180 B
- references/scorer-calibration/raw/skill-name-only.json 182 B
- references/source-context.yaml 10.0 KB
- references/task-profile.json 1.2 KB
- references/technical-writer-devrel-communication-accessible-and-inclusive-writing.md 7.4 KB
- references/technical-writer-devrel-communication-articles-and-long-form.md 8.2 KB
- references/technical-writer-devrel-communication-clarity-style-and-revision.md 9.0 KB
- references/technical-writer-devrel-communication-content-design-and-service-docs.md 8.9 KB
- references/technical-writer-devrel-communication-developer-education.md 7.7 KB
- references/technical-writer-devrel-communication-devrel-role-and-audience.md 8.1 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 79 lines · 63 tokens per session scan A cabbdd3af110
technical-writer is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,587 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
ad-creative
Plan and produce advertising concepts, copy variants, visual directions, and test matrices for paid campaigns.
humanizer-zh
Revise Chinese text to sound specific, fluent, restrained, and human while preserving facts and author intent.
skill-creator
Design and write concise reusable KunAgent skills with valid triggers, real tools, and testable completion criteria.
daily-brief
Produce a dated, source-linked daily brief with prioritized developments, implications, and watch items.
imf-data
Retrieve and analyze IMF macroeconomic series, forecasts, and reserve-composition data.
scholar-research
Search, screen, synthesize, and cite scholarly literature and author metadata.