Avoid AI Writing
conorbronsdon/avoid-ai-writing
Audit and rewrite content to remove AI writing patterns ("AI-isms").
Founder-report packaging stage for the Diffmode growth-tactics pipeline — the post-gate step that turns the APPROVED synthesis.md (a reviewer-facing working paper) into growth-tactics.md, the…
$ npx skills add acogood/diffmode_free --skill founder-report -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install acogood/diffmode_free founder-report --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/acogood/diffmode_free.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugin/skills/founder-report .claude/skills/founder-report && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "founder-report" agent skill from https://github.com/acogood/diffmode_free/tree/main/plugin/skills/founder-report into .claude/skills/founder-report/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "founder-report", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/acogood/diffmode_free/tree/main/plugin/skills/founder-reportType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add acogood/diffmode_free --skill founder-report -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install acogood/diffmode_free founder-report --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/acogood/diffmode_free.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugin/skills/founder-report .agents/skills/founder-report && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "founder-report" agent skill from https://github.com/acogood/diffmode_free/tree/main/plugin/skills/founder-report into .agents/skills/founder-report/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "founder-report", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add acogood/diffmode_free --skill founder-report -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install acogood/diffmode_free founder-report --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/acogood/diffmode_free.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugin/skills/founder-report .cursor/skills/founder-report && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "founder-report" agent skill from https://github.com/acogood/diffmode_free/tree/main/plugin/skills/founder-report into .cursor/skills/founder-report/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "founder-report", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/acogood/diffmode_free.git --path plugin/skills/founder-report--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add acogood/diffmode_free --skill founder-report -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install acogood/diffmode_free founder-report --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/acogood/diffmode_free.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugin/skills/founder-report .gemini/skills/founder-report && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "founder-report" agent skill from https://github.com/acogood/diffmode_free/tree/main/plugin/skills/founder-report into .gemini/skills/founder-report/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "founder-report", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install acogood/diffmode_free founder-reportInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add acogood/diffmode_free --skill founder-report -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/acogood/diffmode_free.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugin/skills/founder-report .github/skills/founder-report && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "founder-report" agent skill from https://github.com/acogood/diffmode_free/tree/main/plugin/skills/founder-report into .github/skills/founder-report/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "founder-report", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add acogood/diffmode_free --skill founder-report -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install acogood/diffmode_free founder-report --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/acogood/diffmode_free.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugin/skills/founder-report .opencode/skills/founder-report && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "founder-report" agent skill from https://github.com/acogood/diffmode_free/tree/main/plugin/skills/founder-report into .opencode/skills/founder-report/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "founder-report", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
founder-reportFounder-report packaging stage for the Diffmode growth-tactics pipeline — the post-gate step that turns the APPROVED synthesis.md (a reviewer-facing working paper) into growth-tactics.md, the…
Founder Report is an agent skill from acogood/diffmode_free. Founder-report packaging stage for the Diffmode growth-tactics pipeline — the post-gate step that turns the APPROVED synthesis.md (a reviewer-facing working paper) into growth-tactics.md, the founder-facing "Your Growth Tactics" report. Strict re-packaging per the central writing-style.md — plain tactic cards (what it is, why they won't see it coming, how to start this week, time to first signal, what you need, kill it if) with ZERO pipeline plumbing — no vector IDs, no Pass labels, no pools, no numeric scores…
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Writing & Content, covering Brand voice and tone. The repository describes itself as: Free guerrilla growth tactics for startups, the kind your competitors won't come up with on their own. Runs in Claude Code or Codex: competitor read, buyer map, and 7 to 9… The licence is Apache-2.0.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit c175a4d. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Founder Report loads about 2.2k tokens when it runs. Until then it costs about 200 tokens; SKILL.md has 1,112 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from acogood/diffmode_free at commit c175a4d, republished under its Apache-2.0 licence (© acogood). 1,112 words, ~2,242 tokens.
.claude/skills/founder-report/SKILL.md (or your agent's skills folder).synthesis.md into "Your Growth Tactics"synthesis.md is written to pass a reviewer: it carries disposition tables, traceability
lines, pool audits, and self-grades, because downstream checks parse them. That makes it a
working paper, not a deliverable. This stage derives the founder view: it reads the
APPROVED synthesis.md and re-packages the tactics into growth-tactics.md — the page the
founder actually opens first. synthesis.md itself is never modified (its structure is
a load-bearing contract with the reviewer and the orchestrator's checks).
Zero new content. Every sentence in the output must be traceable to something
synthesis.md already says. Specifically:
— [Pass 1 White Space] / — [Pass 2 Synergy/Founder-Fit]
origin labels from titles, and strip [HIGH COMPLEXITY] / [LOW CONFIDENCE] flags from
names. Where such a flag exists, say it in plain words inside the card instead (e.g. "this
is the heaviest lift in the set" under What you need).writing-style.md. Nothing else.WS/03-think-tanks/demand-generation/synthesis.md (PRIMARY — the APPROVED final
synthesis; read-only)${CLAUDE_PLUGIN_ROOT}/reference/writing-style.md (the voice contract — grade 6–8,
≤~20 words per sentence, banned-jargon table, the coffee test)WS/03-think-tanks/demand-generation/growth-tactics.md (write no other files)# Your Growth TacticsA 2-3 sentence intro: what these tactics are, why they fit THIS founder (pull the budget / team / stage facts from the Synthesis Overview's Constraint Summary), and how to use the document (start with the quick wins, read each card before committing).
## Start this weekThe tactics whose first signal arrives within ~4 weeks — take them from the Tactical Clusters quick-wins group. One line each: the tactic name + what you'd do first. No card detail here; the cards follow.
## The tacticsOne card per tactic, in synthesis order. Heading: ### N. <Name> (sequential number, plain
name, no bracket labels). Each card has exactly these 7 fields, in this order:
| Field | Built from (synthesis.md) | Rules |
|---|---|---|
| What this is | In plain English (+ Emergent Mechanism where it clarifies) | 1-3 short sentences; what you actually do |
| Why they won't see it coming | Structural Advantage (+ the competitive-adoption note from Primary Channel(s)) | lead with why competitors won't think of this themselves; strip taxonomy labels ("Type: …") — keep the plain structural reason and how long the edge lasts. KEEP competitor-adoption lines like "nobody in your market does this yet" |
| How to start this week | How to Execute steps, kept verbatim where they're already plain | fold in useful Adapted to Your Constraints context (e.g. "scaled down to fit your $500/month") |
| Time to first signal | Expected Timeline & Success Metrics | the early signal + when to expect it; strip any (per …) vector citations |
| What you need | Required Resources (+ Skills Required where it adds something) | time / budget / tools, in one or two lines |
| Kill it if… | the decision point in Expected Timeline & Success Metrics | the concrete number/date that says stop or double down |
| Execute this | derived from the tactic's first steps | 2-3 specific tools, skills, or templates that help execute the first steps — see rules below |
"Execute this" rules. This field is the ONE exception to the "zero new content" rule — it names execution aids, not strategic claims. Scope it tightly:
cold-email skill (coreyhaines31/marketingskills) or the
agent's built-in writingcopywriting skill or the agent's built-in writingfree-tools skill, or the agent's code generationcommunity-marketing or social skillcontent-strategy or ai-seo skill→ <what>: <tool/skill name>.→ No tools needed — this is a shoes-on-the-ground play.## What to avoidFrom the Anti-Portfolio. Per item: why founders try it, why it fails for THIS founder, and what to do instead (point at the relevant card by number). No severity labels, no "anti-pattern" vocabulary — just plain warnings.
## How to sequence theseThe timeline clusters in plain words (this week / this month / the long game), then the Top 5 as "if you only run five, run these" — each with a one-line plain reason taken from what synthesis.md already says about it (fit, speed, the edge). No numeric scores anywhere — the founder gets reasons, not grades.
## Where these came fromOne short paragraph: these tactics were built by combining growth mechanisms mined from real, public case studies during this run, and checked against this founder's budget, team, and stage; the reason they're defensible is that copying them would force a bigger competitor to work in a way their structure doesn't allow. Then point the curious reader at the two working papers in the same report: How These Were Built (the mechanism combinations) and Tactic Engineering Notes (the full engineering write-up, scores and traceability included). This must be the LAST section.
The orchestrator rejects the output if any of these appear. Self-grep before returning:
| Banned | Why |
|---|---|
vector IDs — regex (struct|lever|resource|psych|pos|conv)-[0-9] | plumbing; lives in synthesis.md only |
Pass 1 / Pass 2 | pipeline phase labels |
must_include | constraints plumbing |
Pool A / Pool B | constraints plumbing |
white space / white-space (any case) | pipeline vocabulary |
growth-factors.json | internal file name |
PASS / FAIL self-grading | the founder report doesn't grade itself |
/10 or /50 scores | no numeric scores in the founder view |
| "anti-pattern" (any case) | jargon; say what to avoid in plain words |
Plus everything writing-style.md already bans (leverage, optimize, arbitrage, …).
## The tactics == the number of ### Tactic #N blocks in
synthesis.md, same order, same names (minus bracket tags).## Where these came from.writing-style.md.This stage is best-effort by design: if it can't produce a clean output, the pipeline
ships synthesis.md as the main page (old behavior). Never degrade synthesis.md to make
this stage pass.
© acogood, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in plugin/skills/founder-report of acogood/diffmode_free.
Open the folder on GitHubat commit c175a4d
Founder Report next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Founder Report this skillacogood/diffmode_free | 163 | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| Avoid AI Writingconorbronsdon/avoid-ai-writing | 4.9k | 3 repos | ~8.1k | Automated safety check: Pass | MIT | |
| BrandOhh-889/skyroc | 795 | 13 repos | ~733 | Automated safety check: Pass | MIT | |
| Khazix WeChat Article WriterKKKKhazix/khazix-skills | 21k | 1 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Writing Guidelinesvercel-labs/agent-skills | 32k | 7 repos | ~309 | Automated safety check: Pass | None | |
| Unslop AI Writing Cleanuptheclaymethod/unslop | 516 | — | ~1.7k | Automated safety check: Pass | MIT |
conorbronsdon/avoid-ai-writing
Audit and rewrite content to remove AI writing patterns ("AI-isms").
Ohh-889/skyroc
Brand voice, visual identity, messaging frameworks, asset management, brand consistency.
KKKKhazix/khazix-skills
Writes long-form WeChat official account articles in the personal style of the Khazix account, from briefs, links, PDFs or rough notes, with a topic quality check.
vercel-labs/agent-skills
Review docs/prose for Writing Guidelines compliance. An agent skill from vercel-labs/agent-skills.
theclaymethod/unslop
Removes AI writing tells from prose through an audit-first flow, routing to a two-pass rewrite, a report-only cleanup, voice teaching or mimicry depending on the sub-command used.
content-designer/ux-writing-skill
Applies UX writing practice to interface copy such as buttons, errors, forms and onboarding, using four quality standards and accessibility guidance.
acogood/diffmode_free
Parameterized quality reviewer for Diffmode growth-tactics outputs across the whole pipeline.
acogood/diffmode_free
Competitive gap analysis for a founder's product — a Diffmode growth-tactics think-tank research stage (prompt TT-DG-002).
acogood/diffmode_free
Cross-industry tactic transfer for a founder's product — a Diffmode growth-tactics think-tank research stage (prompt TT-DG-001).
acogood/diffmode_free
Comprehensive acquisition-tactics audit for a founder's industry (AI-CMO enrichment ENR-004).
acogood/diffmode_free
Advanced JTBD + audience segmentation for a founder's product (AI-CMO enrichment ENR-001).
acogood/diffmode_free
Deep competitive-intelligence analysis for a founder's product (AI-CMO enrichment ENR-002).
Categories
Founder-report packaging stage for the Diffmode growth-tactics pipeline — the post-gate step that turns the APPROVED synthesis.md (a reviewer-facing working paper) into growth-tactics.md, the…. Founder Report is an agent skill from acogood/diffmode_free.md, the founder-facing "Your Growth Tactics" report.
Founder Report fits situations like: tasks that involve Brand voice and tone.
Run `npx skills add acogood/diffmode_free --skill founder-report -a claude-code`. Or copy the skill folder (plugin/skills/founder-report in acogood/diffmode_free) into .claude/skills/founder-report in your project. Claude Code loads it when a task matches its description.
Run `npx skills add acogood/diffmode_free --skill founder-report -a codex`. Or copy the skill folder (plugin/skills/founder-report in acogood/diffmode_free) into .agents/skills/founder-report in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add acogood/diffmode_free --skill founder-report -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/founder-report, .gemini/skills/founder-report, .github/skills/founder-report and .opencode/skills/founder-report in your project.
SKILL.md names no scripts, command-line tools or credentials: Founder Report is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Founder Report is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.2k tokens (SKILL.md is roughly 9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Founder Report: Avoid AI Writing (conorbronsdon/avoid-ai-writing, 4.9k stars), Brand (Ohh-889/skyroc, 795 stars), Khazix WeChat Article Writer (KKKKhazix/khazix-skills, 21k stars) and Writing Guidelines (vercel-labs/agent-skills, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
acogood (a GitHub user) maintains it in acogood/diffmode_free, which has 163 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on August 10, 2026.
Source: acogood/diffmode_free on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.