Not in the top 1,000 by GitHub stars
danicat/speedgrapher
Technical writing assistant, side-panel Markdown editor, Model Context Protocol (MCP) server, and Agent Skills suite for Antigravity: Gunning Fog readability, AI slop detection, Vale linting, and SEO/GEO.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/draft/SKILL.md
Week of Nov 2, 2026 · +1 / −1 lines
Before Not checked yet → After Instructions only
e93f24906ea1 → f13434b33285
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → e93f24906ea1
No earlier version was observed for comparison.
skills/ideate/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
e93f24906ea1 → f13434b33285
A local comparison is unavailable. You can inspect the recorded versions on GitHub.
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → e93f24906ea1
No earlier version was observed for comparison.
skills/publish/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
e93f24906ea1 → f13434b33285
A local comparison is unavailable. You can inspect the recorded versions on GitHub.
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → e93f24906ea1
No earlier version was observed for comparison.
skills/readability/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
e93f24906ea1 → f13434b33285
A local comparison is unavailable. You can inspect the recorded versions on GitHub.
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → e93f24906ea1
No earlier version was observed for comparison.
skills/speedgrapher/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
e93f24906ea1 → f13434b33285
A local comparison is unavailable. You can inspect the recorded versions on GitHub.
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → e93f24906ea1
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit f13434b33285c5aba297f57c657974492808eb68
git clone --filter=blob:none --no-checkout https://github.com/danicat/speedgrapher.git .hotskills/danicat-speedgrapher && git -C .hotskills/danicat-speedgrapher checkout --detach f13434b33285c5aba297f57c657974492808eb68
# Copy each selected skill directory from .hotskills/danicat-speedgrapher into .agents/skills/<skill-name>/52GitHub stars
1star in 7 days
5skills in this repository
9commits in 30 days
Heat
2.9- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- draft
skills/draft - ideate
skills/ideate - publish
skills/publish - readability
skills/readability - speedgrapher
skills/speedgrapher
How it works
draft
When your agent uses it
Adaptive-voice technical writing workflow that drafts and expands engineering blog posts, tutorials, READMEs, and documentation matching the author's natural style.
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
2,294 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. End-to-End Drafting Workflow
- 2. Core Editorial Pillars
- 3. First-Draft Anti-Slop & Anti-Jargon Guardrails
- 4. Google Developer Brand & Legal Safety
- 5. Mandatory Pre-Delivery Verification Gate
- Operational Constraints
Files
SKILL.mdcore9,712 bytesSKILL.mdcore9,712 bytes
Read SKILL.md
# Draft: Adaptive-Voice Technical Writing
`draft` transforms structured outlines, interview briefs, and raw engineering notes into clear, authoritative, human-grade technical prose. You never impose a generic machine persona; instead, you fingerprint and replicate the author's natural voice while enforcing strict structural, pedagogical, citation, and brand-safety standards from the very first paragraph.
---
## 1. End-to-End Drafting Workflow
Follow this five-stage workflow whenever authoring or expanding a technical document:
```mermaid
flowchart LR
Voice["1. Voice Fingerprinting\nInspect workspace style & posts"] --> Framing["2. Outcome-First Framing\n150-word lead & GEO section leads"]
Framing --> Pedagogy["3. Grounded Drafting\nWhy-before-how code & citations"]ideate
When your agent uses it
Socratic technical discovery and inverted-pyramid outlining workflow that interviews engineers one question at a time and structures blog posts, READMEs, and documentation by descending reader value.
What it loads into context
Frontmatter
109 tokensAlways available to the agent
SKILL.md
2,809 tokensWhen the skill is activated
Reference documents
2,294 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Mode Selection: Discovery Interview vs. Direct Structural Outlining
- 2. Socratic Discovery: The 4 Pillars of Information Gain
- 3. Inverted-Pyramid Information Architecture
- 4. Document-Specific Structural Sequences
- 5. Deliverable: Structured Brief & Inverted-Pyramid Outline Template
- Operational Constraints
Files
../draft/SKILL.mddoc9,712 bytesSKILL.mdcore12,416 bytes
Read SKILL.md
# Ideate: Socratic Discovery & Inverted-Pyramid Outlining
`ideate` unifies two foundational pre-writing disciplines: **Socratic technical interviewing** (extracting high-information-gain engineering reality before a single paragraph is drafted) and **Inverted-Pyramid Information Architecture** (ordering every document by descending reader value).
---
## 1. Mode Selection: Discovery Interview vs. Direct Structural Outlining
Choose your entry point based on how much raw material is already in context:
1. **Interactive Socratic Interview (Default for New Blog Posts & Articles)**:
- When the user wants to brainstorm a post or says *"interview me about X"*, conduct a focused Socratic interview **one question at a time** to extract all 4 Pillars before generating the outline.
2. **Direct Inverted-Pyramid Outlining / Structural Refactoring**:
- When the user already provides raw notes, code files, or an existing `README.md` / `SKILL.md` / draft to restructure, inspect the workspace artifacts directly and organize them into the target inverted-pyramid sequence.publish
When your agent uses it
Editorial review and publication readiness workflow that audits prose quality, resolves or injects inline review comments, and verifies technical SEO, GEO, and frontmatter metadata.
What it loads into context
Frontmatter
102 tokensAlways available to the agent
SKILL.md
3,985 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Two-Stage Review & Release Pipeline
- 2. Stage A: Prose Quality Gate & Inline Review Comments (All Markdown Files)
- 3. Stage B: Second-Plane Technical SEO, GEO & Localization Gate
- 4. Technical Localization Rules
- 5. Final Release Checklist Deliverable
- Operational Constraints
Files
SKILL.mdcore15,688 bytes
Read SKILL.md
# Publish: Editorial Review, Inline Annotations & SEO/GEO Release Gate
`publish` is Speedgrapher's unified quality and release gate. It operates in two progressive stages mirroring Speedgrapher's two-plane architecture:
- **Stage A (Prose & Structural Review — All Markdown Files)**: Audits readability (`fog`), AI-trope density (`slop`), static grammar/style (`vale`), macro-narrative flow, and bidirectional inline review comments (`<!-- review: ... -->`).
- **Stage B (Second-Plane Technical SEO, GEO & Localization — Blog Posts & Web Pages)**: Audits discoverability via the `seo` MCP tool (`doc_type: "page"` or `"doc"`), enforces the dual-purpose frontmatter split (`summary` vs. `description`), validates Generative Engine Optimization (GEO) signals, and guides idiomatic multi-language localization.
---
## 1. Two-Stage Review & Release Pipeline
```mermaid
flowchart TD
Target["Target Markdown File (.md)"] --> Comments{"Inline `<!-- review: ... -->`\nMode?"}
Comments -->|Resolve Human Comments| Resolve["Rewrite targeted paragraphs\n& remove resolved comment tags"]readability
When your agent uses it
Technical copyediting workflow that replaces corporate jargon with plain English, removes synthetic AI phrasing, and resolves paragraph-level readability and grammar issues.
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
2,956 tokensWhen the skill is activated
Reference documents
3,634 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Why Technical Prose Gets Bogged Down: The HBR Jargon Insight
- 2. The 5-Dimension AI Slop Purge (`deslopify`)
- 3. Deterministic 4-Step Readability & Copyediting Workflow
- 4. Before & After Transformation Example
- Operational Constraints
Files
SKILL.mdcore11,988 bytesreferences/tropes-and-jargon.mddoc16,379 bytes
Read SKILL.md
# Readability: jargon mitigation, deslopification & copyediting
`readability` turns dense, bureaucratic, or synthetic drafts into clear, human-authored technical prose. It combines three complementary disciplines:
1. **The 4-Step HBR Framework** to remove status-signaling jargon and raw acronyms while preserving technical accuracy.
2. **The 5-Dimension AI Slop Purge (`deslopify`)** to eliminate LLM clichés and re-establish natural syntax.
3. **Per-Paragraph `fog` and `vale` Hotspot Remediation** to fix density issues via Speedgrapher MCP metrics and [`references/tropes-and-jargon.md`](references/tropes-and-jargon.md).
---
## 1. Why Technical Prose Gets Bogged Down: The HBR Jargon Insight
Writing loaded with jargon signals insecurity, not mastery. They found that professionals who feel low status lean on unexpanded acronyms and abstract vocabulary to manufacture authority. The strategy backfires: readers trust plain, concrete explanations more. In ["Does Your Office Have a Jargon Problem?"](https://hbr.org/2021/03/do-you-have-a-jargon-problem) (*Harvard Business Review*, March 2021), Zachariah Brown, Eric M. Anicich, and Adam D. Galinsky analyzed thousands of texts to track why people hide behind buzzwords.
speedgrapher
When your agent uses it
Opens the Speedgrapher side-panel Markdown editor in the Antigravity auxiliary pane by surfacing a sidecar://speedgrapher/panel/ pill in chat.
What it loads into context
Frontmatter
107 tokensAlways available to the agent
SKILL.md
311 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Displaying the Side-Panel Pill
Files
SKILL.mdcore1,116 bytes
Read SKILL.md
# Speedgrapher: Side-Panel Launcher
Surfaces a `sidecar://speedgrapher/panel/` pill in chat to open the Speedgrapher side-panel Markdown editor in the auxiliary pane.
## Displaying the Side-Panel Pill
1. **Resolve the target `.md` file (if any)**:
- If the user passed a filename or path, or if a specific `.md` file is in scope, resolve its absolute path on disk.
2. **Output the `sidecar://` pill in chat** (using the file's basename as the link label when a file is known):
- **With a target `.md` file**:
```markdown
[file.md](sidecar://speedgrapher/panel/?file=/absolute/path/to/file.md)
```
- **Without a specific file**:Skills included
- draft
- ideate
- publish
- readability
- speedgrapher
Repository facts
- License
- Apache-2.0
- Created
- Jul 29, 2025
- Last pushed
- Nov 5, 2026
- Forks
- 8
- Open issues
- 0
- Project activity
- Active
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 1 note
skills/draft/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 26 network referencesin 4 files: publish/SKILL.md:56 draft/SKILL.md:58 readability/references/tropes-and-jargon.md:9 and 1 more
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 26 signals by file
skills/draft/SKILL.md
- Network accessline 58
Anchor every tool, library, standard, and specification to its authoritative upstream source: - **Hyperlink Canonical Names on First Mention**: - ✅ `We validated the schema against the [Agent Skills specification](https://agentskills.io) - Network accessline 58
Anchor every tool, library, standard, and specification to its authoritative upstream source: - **Hyperlink Canonical Names on First Mention**: - ✅ `We validated the schema against the [Agent Skills specification](https://agentskills.io) - Network accessline 59
- **Hyperlink Canonical Names on First Mention**: - ✅ `We validated the schema against the [Agent Skills specification](https://agentskills.io) and exposed the tools over the [Model Context Protocol](https://modelcontextprotocol.io).` - - Network accessline 59
- **Hyperlink Canonical Names on First Mention**: - ✅ `We validated the schema against the [Agent Skills specification](https://agentskills.io) and exposed the tools over the [Model Context Protocol](https://modelcontextprotocol.io).` - - Network accessline 60
- ✅ `We validated the schema against the [Agent Skills specification](https://agentskills.io) and exposed the tools over the [Model Context Protocol](https://modelcontextprotocol.io).` - Network accessline 60
- ✅ `We validated the schema against the [Agent Skills specification](https://agentskills.io) and exposed the tools over the [Model Context Protocol](https://modelcontextprotocol.io).` - Network accessline 61
- ✅ `Run [Vale](https://vale.sh) in your pre-commit hook.` - Network accessline 61
- ✅ `Run [Vale](https://vale.sh) in your pre-commit hook.` - Network accessline 62
- **Never Print Bare URLs in Prose**: Do not expose raw URLs (`https://...`) or unformatted domain names inside narrative sentences. - Network accessline 62
- **Never Print Bare URLs in Prose**: Do not expose raw URLs (`https://...`) or unformatted domain names inside narrative sentences.
skills/publish/SKILL.md
- Network accessline 56
1. **Inverted-Pyramid & Macro-Narrative Momentum**: Does the opening 150 words state the core problem, solution, and headline metric? Do later sections maintain forward momentum without re-litigating the introduction? 2. **Functional Precis - Network accessline 57
2. **Functional Precision vs. Status-Signaling Jargon**: Are domain acronyms defined on first use? Have bureaucratic noun stacks been replaced with active verbs? 3. **Canonical Citation Hygiene**: Are tools, libraries, and open standards hy - Network accessline 58
3. **Canonical Citation Hygiene**: Are tools, libraries, and open standards hyperlinked by their canonical name on first mention (for example, `[Model Context Protocol](https://modelcontextprotocol.io)`), with zero bare URLs printed in pros - Network accessline 121
| **`summary`** | **80–180 chars** | Human readers browsing blog index cards, RSS feeds, and newsletters | Write a compelling editorial hook that highlights the engineering tension or debugging story without giving away every detail. | `"Wh - Network accessline 123
| **`canonical`** | **Valid HTTPS URL** | Search engine crawlers (`<link rel="canonical">`) | Specify the authoritative URL for syndicated or cross-posted articles. | `"https://example.dev/blog/zero-alloc-json-go/"` | - Network accessline 129
summary: "When our telemetry cluster hit 40% CPU in reflection stalls, we replaced encoding/json with a pre-compiled column reader." description: "Learn how to build a zero-allocation JSON column reader in Go 1.27 that cuts CPU overhead by - Network accessline 130
description: "Learn how to build a zero-allocation JSON column reader in Go 1.27 that cuts CPU overhead by 44% and keeps p99 latency under 1.2 ms." canonical: "https://example.dev/blog/zero-alloc-json-go/" tags: ["go", "performance", "json" - Network accessline 131
canonical: "https://example.dev/blog/zero-alloc-json-go/" - Network accessline 153
4. **`Heading Hierarchy & Sentence Case`**: Headings descend sequentially (`H1` $\rightarrow$ `H2` $\rightarrow$ `H3`) with zero skipped levels and use strict sentence case. 5. **`Descriptive Image Alt-Text`**: Image `alt` attributes descri - Network accessline 154
5. **`Descriptive Image Alt-Text`**: Image `alt` attributes describe the architectural state or chart trend (`>= 10 chars`), never raw filenames (`diagram.png`) or generic placeholders (`image`, `screenshot`). 6. **`Link & Anchor Hygiene`** - Network accessline 155
6. **`Link & Anchor Hygiene`**: Links use descriptive domain noun phrases (`[Go memory model specification](https://go.dev/ref/mem)`) rather than vague anchors (*"click here"*, *"read more"*) or bare URLs in prose.
skills/readability/SKILL.md
- Network accessline 27
Writing loaded with jargon signals insecurity, not mastery. They found that professionals who feel low status lean on unexpanded acronyms and abstract vocabulary to manufacture authority. The strategy backfires: readers trust plain, concret
skills/readability/references/tropes-and-jargon.md
- Network accessline 9
As demonstrated by Zachariah Brown, Eric M. Anicich, and Adam D. Galinsky in [*"Does Your Office Have a Jargon Problem?"*](https://hbr.org/2021/03/do-you-have-a-jargon-problem) (*Harvard Business Review*, March 2021), communicators experien - Network accessline 94
| **Throat-Clearing Openings** | *In today's fast-paced world...* / *Imagine a world where...* | Wastes the first paragraph on truisms before introducing the actual technical problem. | In today's fast-paced cloud-native world, microservice - Network accessline 95
| **Patronizing Analogy** | *Think of it as a Swiss Army knife / highway system...* | Interrupts technical explanations with clichés that are less accurate than the mechanism itself. | Think of a mutex like a single-occupancy restroom key s - Network accessline 96
| **Vague Attribution** | *Experts argue...* / *Industry reports suggest...* | Appeals to unnamed authority instead of citing a specific benchmark, RFC, or incident report. | Industry experts argue that tail latency matters more than averag
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 26 facts
- Network access in prose of the SKILL.mddraft/SKILL.md:58Low confidence
- Network access in prose of the SKILL.mdskills/draft/SKILL.md:58Low confidence
- Network access in prose of the SKILL.mddraft/SKILL.md:59Low confidence
- Network access in prose of the SKILL.mdskills/draft/SKILL.md:59Low confidence
- Network access in prose of the SKILL.mddraft/SKILL.md:60Low confidence
- Network access in prose of the SKILL.mdskills/draft/SKILL.md:60Low confidence
- Network access in prose of the SKILL.mddraft/SKILL.md:61Low confidence
- Network access in prose of the SKILL.mdskills/draft/SKILL.md:61Low confidence
- Network access in prose of the SKILL.mddraft/SKILL.md:62Low confidence
- Network access in prose of the SKILL.mdskills/draft/SKILL.md:62Low confidence
- Network access in prose of the SKILL.mdpublish/SKILL.md:56Low confidence
- Network access in prose of the SKILL.mdpublish/SKILL.md:57Low confidence
- Network access in prose of the SKILL.mdpublish/SKILL.md:58Low confidence
- Network access in prose of the SKILL.mdpublish/SKILL.md:121Low confidence
- Network access in prose of the SKILL.mdpublish/SKILL.md:123Low confidence
- Network access in code of the SKILL.mdpublish/SKILL.md:129High confidence
- Network access in code of the SKILL.mdpublish/SKILL.md:130High confidence
- Network access in code of the SKILL.mdpublish/SKILL.md:131High confidence
- Network access in prose of the SKILL.mdpublish/SKILL.md:153Low confidence
- Network access in prose of the SKILL.mdpublish/SKILL.md:154Low confidence
- Network access in prose of the SKILL.mdpublish/SKILL.md:155Low confidence
- Network access in prose of the SKILL.mdreadability/SKILL.md:27Low confidence
- Network access in prose of documentationreadability/references/tropes-and-jargon.md:9Low confidence
- Network access in prose of documentationreadability/references/tropes-and-jargon.md:94Low confidence
- Network access in prose of documentationreadability/references/tropes-and-jargon.md:95Low confidence
- Network access in prose of documentationreadability/references/tropes-and-jargon.md:96Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/draft/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest rules/AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/draft/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/draft/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/draft/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/draft/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
