Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Writing Pov

ASecurity

Audits point-of-view for violations, consistency, and fit. Use when narration feels inconsistent, when there is unwanted head-hopping, or when the chosen POV isn't serving the story. Triggers: 'POV problems', 'head-hopping', 'point of view', 'the narration feels inconsistent', 'POV violations', 'narrative perspective', 'sometimes we know things the character shouldn't'.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsrustgo

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill writing-pov --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Writing Pov?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Writing Pov
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-writing-pov/badge)](https://www.skillsdirectory.com/skills/rondoflow-writing-pov)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: writing-pov
description: "Audits point-of-view for violations, consistency, and fit. Use when narration feels inconsistent, when there is unwanted head-hopping, or when the chosen POV isn't serving the story. Triggers: 'POV problems', 'head-hopping', 'point of view', 'the narration feels inconsistent', 'POV violations', 'narrative perspective', 'sometimes we know things the character shouldn't'."
---

# Writing: Point of View

POV is a contract with the reader about what the narration can know. The moment that contract is violated — the moment the narration accesses something it has promised not to access — the reader's trust breaks. Usually they don't know why. They just feel the seam, the moment the author's hand becomes visible. "How did we know that?" is the diagnostic question.

Each POV type makes a different promise:

**First person:** The narrator tells us what they experienced, observed, thought, and felt. They cannot know what other characters are thinking unless they are told or infer it (and the inference should be flagged as inference). They can be unreliable — their account of events may be shaped by their psychology, their blindspots, their desire to present themselves well.

**Close third person:** Narration follows one character's subjective experience. The narration can access their thoughts and feelings but cannot access anyone else's interior. Physical details that the POV character couldn't observe (what their own face looks like, what's happening in a room they're not in) require specific handling. Thought and feeling are rendered from inside, not described from outside.

**Omniscient:** The narrator has access to any mind. But omniscient POV is not a licence for chaos — it must be used consistently. An omniscient narrator who dips into three minds in one scene and then goes external in the next has not chosen omniscient POV; they have abandoned POV control entirely.

The fit question is as important as the violation question: does the chosen POV serve what the story is trying to do? A story whose power lives in dramatic irony (the reader knows something the protagonist doesn't) may work better in third than first. A story whose power is unreliable memory may need first person. The POV choice is not arbitrary — the story's core effect often depends on it.

---

## Your Process

**Step 1: Identify Current POV Type**
First person / close third / omniscient / second person / mixed. If mixed, is it intentionally mixed (multiple POV characters with clear transitions) or unintentionally mixed (the narration drifts without structure)?

**Framing check:** Confirm the specific text and POV situation before continuing. State what you've identified — the POV type, the POV character (if applicable), and whether the concern is violations, fit, or both — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the text and its POV situation]. Is that right?"
- **Header:** "Framing"
- **Options:**
  - **Yes — proceed** — framing is correct
  - **Adjust** — one element is off; user will correct it before you continue
  - **Reframe** — different situation than read; incorporate the correction before proceeding

**Step 2: State the Contract**
What does this POV promise about access to interiority? First person: access to the narrator's interior, inference about others. Close third: access to POV character's interior, not others'. Omniscient: access to any interior, but must be applied consistently. State the contract explicitly — it becomes the audit standard.

**Step 3: Scan for Violations**
Violations fall into four categories:
- **Interiority violations:** Narration accesses another character's thoughts or feelings without the POV character being told or inferring
- **Observation violations:** Narration describes something the POV character couldn't see, hear, or observe
- **Knowledge violations:** Narration assumes knowledge the POV character doesn't have
- **Inconsistency violations:** The POV type shifts without transition (close third suddenly going omniscient for one paragraph)

For each violation: quote the line, identify the type, name what was accessed that couldn't be accessed.

**Step 4: Fit Assessment**
Does the chosen POV serve the story's core effect? Consider:
- If the story's power is in *not knowing* something — close third may serve better than omniscient
- If the story's power is in the narrator's *voice and personality* — first person may be more powerful
- If the story requires events the protagonist can't witness — close third may be limiting; omniscient or multiple POV may be needed
- If dramatic irony is central — omniscient or multiple POV enables it; first-person limits it

---

## Human Check-in

Before proceeding, use the `AskUserQuestion` tool. State your interpretation of the situation in 1–2 sentences — what is being analyzed and what the core question is — then ask:

- **Question:** "My read: [your 1–2 sentence interpretation]. How do you want to proceed?"
- **Header:** "Scope"
- **Options:**
  - **Full analysis** — Complete all steps, reasoning shown throughout
  - **Key findings only** — Bottom-line output, skip step-by-step detail
  - **Specific focus** — Zoom in on one aspect of this analysis
  - **Reframe** — The read is off; correct it and the analysis will follow the corrected framing

Proceed based on their selection. If the user reframes, incorporate the correction before running any analysis.

---

## Output Format

### POV Audit

**Type Identified:** [First person / Close third / Omniscient / Second / Mixed — and whether mixed is intentional]

**Contract Stated:** [What this POV promises about access to interiority and observation]

**Violations:**
- [Quoted line] — Type: [Interiority / Observation / Knowledge / Inconsistency] — What was accessed that couldn't be
- [Repeat for each violation]
- NONE FOUND if clean

**Fit Assessment:** [Does this POV serve the story's core effect? What would be gained or lost by changing it?]

**Recommendation:** [Maintain current POV with fixes / Consider switching to X because Y]

---

## Notes

- POV violations are a type of continuity error, but they require their own audit pass because they operate at the narrative level rather than the story level.
- The hardest violations to catch in close third: the narrator describing what the POV character's own face looks like (characters don't see their own faces), and the narration accessing physical sensations the POV character has gone numb to (because the author needs the reader to feel them).
- Pairs with `/writing-voice-consistency` — POV and voice are linked; a close-third narration that suddenly takes on the author's philosophical voice rather than the character's is both a POV violation and a voice inconsistency.
- Pairs with `/writing-inconsistency-audit` — POV violations are logged there as a category; this skill provides the deeper analysis when they're numerous or the POV choice itself is the problem.

---

## What's Next

After delivering this output, use `AskUserQuestion` to offer the next move:

- **Question:** "POV established. What's next?"
- **Header:** "Next"
- **Options:**
  - `/writing-voice-consistency` — Ensure POV is voice-consistent throughout
  - `/writing-scene-construction` — Construct scenes from the established POV
  - `/writing-character-development` — Develop the character whose POV this is
  - **Done** — Wrap up and synthesise what we have so far

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →