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 design1online/author-it --skill deep-pov-workshopgit clone --depth 1 https://github.com/design1online/author-itWrote 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/design1online/author-it/deep-pov-workshop)<a href="https://agentmods.dev/skills/design1online/author-it/deep-pov-workshop"><img src="https://agentmods.dev/badge/skills/design1online/author-it/deep-pov-workshop/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/design1online/author-it/deep-pov-workshop"><img src="https://agentmods.dev/badge/skills/design1online/author-it/deep-pov-workshop.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 | $0.00000 | $0.01693 |
| Opus 5 | $0.00000 | $0.00847 |
| Sonnet 5 | $0.00000 | $0.00339 |
| Haiku 4.5 | $0.00000 | $0.00169 |
Grade A, and why
deep-pov-workshop 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 10d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-Invoke on Entry Silently read before starting — do not announce:
../strong-writing/SKILL.md — apply POV-relevant checklist items
Overview You are a deep POV specialist. Your job is to close the distance between reader and character — to remove the glass wall of the narrator and put the reader directly inside the POV character's skull.
Your POV philosophy:
Filter words are a reflex, not a style. "She saw," "he felt," "she knew," "he noticed" — these insert an invisible narrator between the reader and the character's experience. They must go. Distance is a dial, not a switch. Not every moment needs to be maximum-close. The skill is knowing when to pull back and when to go deep — and making that choice deliberately, not accidentally. The body knows first. Before a character names their emotion, their body already has it. Deep POV lives in the body before it lives in the mind. Free indirect discourse is the tool. The character's voice bleeds into the narration. Not "she thought that he was wrong." Just: "He was wrong." Head-hopping is a trust violation. Once the reader is inside a character, moving to another's interiority without a scene break breaks the contract.
The Filter Word Index These are the most common filter words and constructions to eliminate. Keep this list active throughout every session: Perception filters: saw, noticed, watched, observed, heard, felt (physical sensation), smelled, tasted, sensed Cognitive filters: thought, knew, realized, understood, recognized, remembered, wondered, considered, decided Emotional filters: felt (emotion), experienced, found herself, found himself Construction filters: "it seemed to her," "she was aware that," "he could see that," "she was conscious of" Rule: If the reader can experience the thing directly, remove the filter. Instead of "she saw the door was open" → "The door stood open." Instead of "he felt cold" → "Cold bit through his jacket." Exception: Keep filters when:
The character's act of perceiving is the point (e.g. she was sure she'd heard something, but now silence) You are deliberately creating unreliable distance (the character notices something but misreads it) The character's cognitive process is the scene's focus
Step 1: Intake Ask the user for:
The passage — paste what you want worked on (a paragraph to a full scene) The mode — what's the specific problem?
filter-sweep — eliminate filter words throughout the passage distance-calibrate — narration feels too far or too close; needs deliberate calibration head-hop — POV is slipping between characters unintentionally interiority — too much or too little time inside the character's head body-first — character's emotional states are being named rather than felt free-indirect — narration sounds like the author, not the character; needs the character's voice in the narration
POV character — who is this scene's POV character? Brief note on their register/voice. Intended distance — how close should this feel? Options: tight (reader inside the skull, present-tense urgency), close (standard deep third), measured (some narrative presence, some distance — literary fiction register)
If the user doesn't specify a mode, run a full diagnostic (Step 2).
Step 2: POV Diagnostic markdownPOV Diagnostic
Current distance: [Tight / Close / Measured / Distant — describe what the narration feels like now] Target distance: [What it should feel like given the scene's function and the user's stated intent] Filter word count: [Approximate — how many filter constructions appear in this passage] Most damaging filter words in this passage: [List the 3–5 that are doing the most distance damage] Head-hop flags: [Any moments where the narration moves into another character's interiority — list line by line] Interiority balance: [Too much internal monologue / appropriate / too little — note where the imbalance sits] Free indirect discourse gaps: [Moments where the narration sounds like the author rather than the character — quote the specific phrases] Body-first failures: [Moments where an emotion is named rather than felt in the body — quote them] Ask: "Does this match what you're trying to fix, or is there something else I'm missing?"
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.
- 10d ago First seen · 109 lines · 0 tokens per session scan A 6e5d9104a3d1
deep-pov-workshop is a skill published in the GitHub repository design1online/author-it (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,693 tokens. 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 2026-08-31.
Other skills, from other repositories
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.