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 SkillMedev/skills --skill cover-letter-writergit clone --depth 1 https://github.com/SkillMedev/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/skillmedev/skills/cover-letter-writer)<a href="https://agentmods.dev/skills/skillmedev/skills/cover-letter-writer"><img src="https://agentmods.dev/badge/skills/skillmedev/skills/cover-letter-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/skillmedev/skills/cover-letter-writer"><img src="https://agentmods.dev/badge/skills/skillmedev/skills/cover-letter-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 | $0.00131 | $0.01689 |
| Opus 5.5 | $0.00052 | $0.00676 |
| Sonnet 5.5 | $0.00026 | $0.00338 |
| Haiku 4.5 | $0.00013 | $0.00169 |
Grade A, and why
cover-letter-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 1mo 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cover Letter Writer
A cover letter has one job - earn a resume read from a screener who spends under thirty seconds on it - and most letters fail in the first sentence by opening with "I am writing to apply for" and then restating the resume the screener is about to read anyway. The costly mistake this skill prevents is the generic letter - one that could be sent to any company with a find-and-replace - because screeners detect those instantly and treat them as evidence of low interest. A tailored letter answers three specific questions the posting is asking and proves the candidate did homework the other applicants skipped.
Operating procedure
Follow these steps in order. Requirement extraction comes before any writing, because the letter's entire structure hangs on which three requirements it answers - draft prose first and the letter drifts back into a resume summary.
- Collect the inputs. Get the resume, the full job posting, and any company hook material (see Inputs below). Do not proceed on the posting title alone; the ranked requirements live in the body text.
- Extract the three requirements the posting cares most about. Rank every stated requirement by three signals - repetition (appears in the summary and again in the bullet list), position (first three bullets outrank the last three), and specificity (a named tool, quota, or scale beats a soft trait like "team player"). Take the top three. Exactly three: fewer looks thin, more dilutes each into a mention instead of an argument.
- Mirror each requirement with resume evidence. For each of the three, find the single strongest proof in the resume - an accomplishment with a number wherever one exists (revenue, users, percent improvement, team size, time saved). Use the posting's own vocabulary in the mirror sentence so a keyword-scanning reader ties evidence to requirement without effort. If the resume has no evidence for a requirement, say so to the user and pick the nearest adjacent proof - do not fabricate.
- Write the company-specific hook as the first line. One sentence that could only be written to this company - a recent launch, a stated mission the candidate genuinely connects to, a product they actually use, a public challenge the role clearly exists to solve. If no hook material was provided, derive one from the posting itself and label it a guess for the user to confirm or replace.
- Assemble the letter. Structure - hook line, one bridge sentence naming the role, one short paragraph (or tight two-sentence block) per mirrored requirement, and a closing line with a plain ask for a conversation. No "To Whom It May Concern"; use the hiring manager's name if known, otherwise the team name.
- Cut to under 300 words. Target 150 to 250. Cut throat-clearing ("I believe that", "I am confident"), any sentence that restates a resume line without adding context, and all adjectives about the candidate's own character ("passionate", "driven") - evidence carries the claim or nothing does.
- Run the quality bar below, then deliver the letter with the three extracted requirements listed so the user can sanity-check the targeting.
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.
- 1mo ago First seen · 89 lines · 131 tokens per session scan A 43c83fa79af4
cover-letter-writer is a skill published in the GitHub repository SkillMedev/skills (19 stars, last pushed 3d ago), licensed MIT. It adds 131 tokens to every session and 1,689 once invoked, about $0.0005 per session on Opus 5.5. 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
customer-journey-map
Construye un mapa de recorrido del cliente para un producto, servicio o experiencia. Úsalo cuando se te pida mapear un recorrido del cliente, crear un viaje del usuario, documentar puntos de contacto y puntos de fricción, o diseñar un mapa de experiencia. Produce un mapa de recorrido completo con etapas, puntos de…
feature-prioritisation
Aplica marcos de priorización (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) para clasificar características e items del backlog. Úsalo cuando se te pida priorizar características, clasificar un backlog, decidir qué construir a continuación, o evaluar compensaciones entre ideas competidoras. Produce una lista de…
outcome-tracker
Record the testable predictions inside a decision, then score them against reality later — so frameworks earn trust from outcomes, not vibes. Use when committing to a prioritisation, forecast, or plan (to log what it predicts), when asked to review what actually happened, or to compute how well-calibrated past RICE…
explorer-pipeline
Use when asked to make an interactive 3D explorer of a topic from start to finish, go from a topic to a clickable 3D learning page, or run the whole 3D explorer process. Produces a staged run of explorer-interface-brief, model-prompt-pack and explorer-viewer-builder in order for one topic, with the hand-offs between…
design-handoff-brief
Transform feature briefs into structured design briefs that give designers the context they need before opening Figma. Use when asked to write a design brief, create a design handoff, brief a designer on a new feature, or translate a PRD into design requirements. Produces a brief with user goal, emotional context…
scenario-zbrush-expert
Use when an agent drives Maxon ZBrush 2026 for any task (sculpt in ZBrush, DynaMesh, ZRemesher, UVs, export, polypaint, posing, 3D print, clean up an AI mesh in ZBrush), when writing ZBrush Python (zbrush.commands) or ZScript, when the ZBrush bridge is not answering, a palette path or set() does nothing, a scripted…